Modeling method for computing features

Abstract

A method for determining a model used to predict overlay precision data associated with a patterned current substrate is described herein. The method involves obtaining (i) a set of first data associated with one or more previous layers and / or a current layer of a current substrate, (ii) a set of second data comprising overlay precision measurement data associated with one or more previous substrates, and (iii) measured overlay precision data associated with the current layer of the current substrate that is not corrected; and determining values for a set of model parameters associated with the model based on (i) the set of first data, (ii) the set of second data, and (iii) the measured overlay precision data that is not corrected, such that the model predicts overlay precision data for the current substrate, where the values are determined to minimize a cost function, and the overlay precision data for the current substrate is not corrected. The cost function includes a difference between the predicted data and the measured overlay precision data that is not corrected.

Description

[0001] This application is a divisional application of the patent application with application number 202080055725.4 and invention name “Modeling method for calculating features”, whose applicant is “ASML Netherlands B.V.” and whose entry date into the Chinese national phase is January 30, 2022 (international application date is July 9, 2020 and international application number is PCT / EP2020 / 069355). Technical Field

[0002] The description herein generally relates to patterning processes and apparatus and methods for determining features corresponding to a design layout. Background Art

[0003] Lithographic projection apparatus may be used, for example, in the manufacture of integrated circuits (ICs). In this case, a patterning device (e.g., a mask) may include or provide a pattern corresponding to a separate layer of the IC (a "design layout"), and this pattern may be transferred to a target portion (e.g., comprising one or more dies) on a substrate (e.g., a silicon wafer) that has been coated with a layer of radiation-sensitive material ("resist"), such as by irradiating the target portion with the pattern on the patterning device. Typically, a single substrate comprises a plurality of adjacent target portions, to which the pattern is transferred successively, one target portion at a time, by the lithographic projection apparatus. In one type of lithographic projection apparatus, the pattern on the entire patterning device is transferred to one target portion at a time; such an apparatus is generally referred to as a stepper. In an alternative apparatus, generally referred to as a stepper-scan apparatus, the projection beam is scanned across the patterning device in a given reference direction (the "scanning" direction), while the substrate is synchronously moved parallel or antiparallel to this reference direction. Different portions of the pattern on the patterning device are progressively transferred to one target portion. Typically, since the lithographic projection apparatus will have a reduction ratio M (e.g. 4), the speed F at which the substrate is moved will be 1 / M times the speed at which the projection beam scans the patterning device. Further information on a lithographic apparatus as described herein can be gleaned, for example, from US 6,046,792, which is incorporated herein by reference.

[0004] Before the pattern is transferred from the pattern forming device to the substrate, the substrate may undergo various processes, such as primer coating, resist coating, and soft baking. After exposure, the substrate may undergo other processes ("post-exposure processes"), such as post-exposure baking (PEB), development, hard baking, and measurement / inspection of the transferred pattern. This series of processes is used as the basis for manufacturing the individual layers of the device (e.g., IC). The substrate may then undergo various processes, such as etching, ion implantation (doping), metallization, oxidation, chemical-mechanical polishing, etc., all of which are intended to complete the individual layers of the device. If several layers are required in the device, the entire process or a variation thereof is repeated for each layer. Ultimately, there will be a device in each target portion on the substrate. These devices are then separated from each other by techniques such as dicing or sawing, so that the individual devices can be mounted on a carrier, connected to pins, etc.

[0005] Therefore, manufacturing devices such as semiconductor devices typically involves using multiple manufacturing processes to process a substrate (e.g., a semiconductor wafer) to form various features and multiple layers of the device. These layers and features are typically manufactured and processed using, for example, deposition, lithography, etching, chemical mechanical polishing, and ion implantation. Multiple devices can be manufactured on multiple dies on a substrate, and then the multiple devices are separated into independent devices. This device manufacturing process can be considered a patterning process. The patterning process involves a patterning step of patterning using a pattern forming device in a lithography device, such as optical and / or nanoimprint lithography, to transfer the pattern on the pattern forming device to the substrate, and the patterning process typically but optionally involves one or more related pattern processing steps, such as resist development by a developing device, baking the substrate using a baking tool, using an etching device and etching using a pattern, etc.

[0006] As mentioned, photolithography is a central step in the manufacture of devices such as ICs, where patterns formed on a substrate define the functional elements of the device, such as microprocessors, memory chips, etc. Similar photolithography techniques are also used to form flat panel displays, microelectromechanical systems (MEMS), and other devices.

[0007] As semiconductor manufacturing processes continue to advance, the size of functional elements has been continuously reduced for decades, while the number of functional elements, such as transistors, per device has been steadily increasing, following a trend generally referred to as "Moore's Law." In the current state of the art, the layers of a device are manufactured using a lithographic projection apparatus that projects a design layout onto a substrate using illumination from a deep ultraviolet illumination source, thereby producing individual functional elements having dimensions well below 100 nm, i.e., less than half the wavelength of the radiation from the illumination source (e.g., a 193 nm illumination source). Summary of the invention

[0008] According to an embodiment, a method for determining a model for predicting overlay accuracy data associated with a current substrate being patterned is described herein, the method comprising: obtaining (i) a set of first data associated with one or more previous layers and / or a current layer of the current substrate being patterned, (ii) a set of second data comprising overlay accuracy measurement data associated with one or more previous substrates patterned prior to the current substrate, and (iii) uncorrected measured overlay accuracy data associated with a current layer of the current substrate; and based on (i) the set of the first data, (ii) the set of the second data and (iii) the uncorrected measured overlay accuracy data, determining a set of values ​​of model parameters associated with the model so that the model predicts overlay accuracy data for the current substrate, wherein the values ​​of the model parameters are determined to minimize a cost function, the cost function comprising the difference between the predicted overlay accuracy data and the uncorrected measured overlay accuracy data.

[0009] Furthermore, in an embodiment, a computer program product is provided. The computer program product includes a non-transitory computer-readable medium, on which instructions are recorded. When the instructions are executed by a computer, the steps of the method described in any one of the above embodiments are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate certain aspects of the subject matter disclosed herein and, together with the “Detailed Description”, help explain some principles associated with the disclosed embodiments. In the drawings,

[0011] Figure 1 A block diagram showing multiple subsystems of a lithography system according to an embodiment;

[0012] Figure 2 describing a lithographic cell or cluster according to an embodiment;

[0013] Figure 3 Schematically illustrating a measurement and exposure process associated with a lithographic apparatus according to an embodiment;

[0014] Figure 4A An exemplary model configured to predict uncorrected overlay accuracy data (or features) according to an embodiment is described;

[0015] Figure 4B Description of the method for training according to the embodiment Figure 4A An exemplary cost function of a model of , the cost function being shown as the difference between a predicted overlay accuracy data map and an uncorrected measured overlay accuracy map;

[0016] Figure 5illustrating exemplary point level data for training a point level model according to an embodiment;

[0017] Figure 6 An exemplary decomposition of an overlay accuracy map based on basis functions associated with both inter-field components and intra-field components according to an embodiment is described;

[0018] Figure 7 is a flow chart of a method for determining a model for predicting uncorrected overlay accuracy data associated with a current substrate being patterned according to an embodiment;

[0019] Figure 8 is used to update uncorrected overlay accuracy data (e.g., Figure 7 Flowchart of the method for training the model;

[0020] Fig. 9 Describing an exemplary overlay accuracy correction based on a predicted overlay accuracy of a previous batch of substrates and a current substrate according to an embodiment;

[0021] Fig.10 is a flow chart of a method for determining an overlay accuracy correction for a current substrate to be patterned according to an embodiment;

[0022] Fig.11 is an example of establishing an overlay accuracy prediction model using alignment data and overlay accuracy data according to an embodiment;

[0023] Fig.12 An example of data (eg, overlay accuracy data) for each field used to train a model according to an embodiment is described;

[0024] Fig.13 illustrating exemplary overlay accuracy data according to an embodiment;

[0025] Fig.14 is a block diagram of an exemplary feed-forward correction of a patterning process according to an embodiment;

[0026] Fig.15 is a flowchart of a method for training a model according to an embodiment;

[0027] Fig.16 According to an embodiment, a Fig.15 A flow chart of a method for controlling a patterning process based on predictions from a trained model;

[0028] Fig.17 schematically depicts an embodiment of a scanning electron microscope (SEM) according to an embodiment;

[0029] Fig.18schematically depicts an embodiment of an electron beam inspection apparatus according to an embodiment;

[0030] Fig.19 schematically depicts an exemplary inspection apparatus and metrology technique according to an embodiment;

[0031] Fig. 20 schematically depicts an exemplary inspection apparatus according to an embodiment;

[0032] Fig.21 Describe the relationship between the illumination light spot and the measurement target of the inspection device according to the embodiment;

[0033] Fig. 22 Schematically depicting a process of deriving a plurality of variables of interest based on measurement data according to an embodiment;

[0034] Fig.23 is a block diagram of an exemplary computer system according to an embodiment;

[0035] Fig.24 is a schematic diagram of a lithographic projection apparatus according to an embodiment;

[0036] Fig.25 is a schematic diagram of another lithographic projection apparatus according to an embodiment;

[0037] Fig.26 According to the embodiment Fig.25 A more detailed view of the devices in

[0038] Fig. 27 According to the embodiment Fig.25 and Fig.26 A more detailed view of the source collector module SO of the device. DETAILED DESCRIPTION

[0039] Although specific reference may be made herein to the manufacture of ICs, it should be clearly understood that the description herein has many other possible applications. For example, the description herein may be used to manufacture integrated optical systems, guidance and detection patterns for magnetic domain memories, liquid crystal display panels, thin film magnetic heads, etc. It will be understood by those skilled in the art that in the context of these alternative applications, any use of the terms "reticle", "wafer" or "die" herein should be considered interchangeable with the more general terms "mask", "substrate" and "target portion", respectively.

[0040] In this document, the terms "radiation" and "beam" are used to cover all types of electromagnetic radiation, including ultraviolet radiation (e.g., having a wavelength of 365 nm, 248 nm, 193 nm, 157 nm or 126 nm) and EUV (extreme ultraviolet radiation, e.g., having a wavelength in the range of about 5 nm to 100 nm).

[0041] The pattern forming device may include or may form one or more design layouts. The design layout may be generated using a CAD (computer-aided design) program, which is often referred to as EDA (electronic design automation). Most CAD programs follow a set of predetermined design rules to generate a functional design layout / pattern forming device. These rules are set by processing and design constraints. For example, the design rules define the spatial tolerance between devices (such as gates, capacitors, etc.) or interconnects to ensure that the devices or lines do not interact with each other in an undesirable manner. One or more of the design rule constraints may be referred to as a "critical dimension" (CD). The critical dimension of a device may be defined as the minimum width of a line or hole, or the minimum space between two lines or two holes. Therefore, the CD determines the overall size and density of the designed device. Of course, one of the goals in device manufacturing is to faithfully reproduce the original design intent on the substrate (via the pattern forming device).

[0042] As an example, pattern layout design may include the application of resolution enhancement techniques, such as optical proximity correction (OPC). OPC addresses the fact that the final size and placement of the image of the design layout projected on the substrate will not be the same as or simply depend on the size and placement of the design layout on the pattern forming device. It should be noted that the terms "mask", "reticle", and "pattern forming device" can be used interchangeably herein. In addition, those skilled in the art will recognize that the terms "mask", "pattern forming device", and "design layout" can be used interchangeably, such as in the context of RET, it is not necessary to use a physical pattern forming device, but the design layout can be used to represent the physical pattern forming device. For smaller feature sizes and higher feature densities present on a certain design layout, the position of a particular edge of a given feature will be affected to some extent by the presence or absence of other adjacent features. These proximity effects originate from a tiny amount of radiation coupled from one feature to another or non-geometric optical effects such as diffraction and interference. Similarly, proximity effects may originate from diffusion and other chemical effects during post-exposure baking (PEB), resist development, and etching after conventional photolithography.

[0043] Before describing the embodiments in detail, it is meaningful to present an exemplary environment in which the embodiments can be implemented.

[0044] Figure 1An exemplary lithographic projection apparatus 10A is illustrated. The main components are a radiation source 12A, which may be a deep ultraviolet excimer laser source or other types of sources including extreme ultraviolet (EUV) sources (as discussed above, the lithographic projection apparatus itself need not have a radiation source); illumination optics, which, for example, define partial coherence (expressed as mean square deviation) and may include optics 14A, 16Aa, and 16Ab that shape the radiation from source 12A; a patterning device 18A; and transmission optics 16Ac that projects an image of the patterning device pattern onto a substrate plane 22A. An adjustable filter or aperture 20A at a pupil plane of the projection optics may limit the range of beam angles impinging on substrate plane 22A, wherein the largest possible angle defines the numerical aperture NA of the projection optics = n sin (θ max ), where n is the refractive index of the medium between the substrate and the last element of the projection optics, and θ max is the maximum angle of the beam emerging from the projection optics that can still impinge on the substrate plane 22A.

[0045] In a lithographic projection apparatus, a source provides illumination (i.e., radiation) to a patterning device, and projection optics directs the illumination onto a substrate via the patterning device and shapes the illumination. The projection optics may include at least some of components 14A, 16Aa, 16Ab, and 16Ac. An aerial image (AI) is a distribution of radiation intensity at the substrate level. A resist layer on the substrate is exposed, and the aerial image is transferred to the resist layer to be a latent "resist image" (RI) therein. The resist image (RI) may be defined as a spatial distribution of the solubility of the resist in the resist layer. A resist model may be used to calculate a resist image from an aerial image, an example of which may be found in U.S. Patent Application Publication No. US2009-0157360, the entire disclosure of which is incorporated herein by reference. The resist model is only related to the properties of the resist layer (e.g., the effects of chemical processes occurring during exposure, PEB, and development). The optical properties of the lithographic projection apparatus (e.g., the properties of the source, the patterning device, and the projection optics) specify the aerial image. Since the patterning device used in a lithographic projection apparatus can be varied, it may be desirable to decouple the optical properties of the patterning device from the optical properties of the rest of the lithographic projection apparatus including at least the source and projection optics.

[0046] Figure 2Depicting a lithographic cell or cluster. The lithographic apparatus LA may form part of a lithographic cell LC (sometimes also referred to as a lithocell or cluster), which also includes equipment for performing pre-exposure processes and post-exposure processes on a substrate. Typically, these equipment include one or more spin coaters SC for depositing one or more resist layers, one or more developers DE for developing the exposed resist, one or more chill plates CH and / or one or more bake plates BK. A substrate handler or robot RO picks up one or more substrates from input / output ports I / O1, I / O2, moves the substrates between different process equipment and transfers the substrates to a feed station LB of the lithographic apparatus. These equipment, often collectively referred to as tracks, are controlled by a track control unit TCU, which itself is controlled by a management control system SCS, which also controls the lithographic apparatus via a lithographic control unit LACU. Thus, different equipment may be operated to maximize throughput and processing efficiency.

[0047] In order to correctly and consistently expose a substrate exposed by a lithographic apparatus, it is desirable to inspect the exposed substrate to measure or determine one or more properties, such as overlay (the overlay may be, for example, between structures in an overlying layer, or between structures in the same layer that have been separately provided to that layer by, for example, a double patterning process), line thickness, critical dimension (CD), focus offset, material properties, etc. Therefore, the manufacturing facility in which the lithocell LC is located typically also comprises a metrology system MET, which receives some or all of the substrates W that have been processed in the lithocell. The metrology system MET may be part of the lithocell LC, for example, it may be part of the lithographic apparatus LA.

[0048] The measurement results may be provided directly or indirectly to the supervisory control system SCS. If an error is detected, the exposure of subsequent substrates (especially if the detection can be completed quickly and quickly enough so that one or more other substrates of the batch remain to be exposed) and / or the subsequent exposure of already exposed substrates may be adjusted. In addition, already exposed substrates may be stripped and reworked to improve yield, or discarded, thereby avoiding further processing of substrates known to be defective. In the case where only some target portions of the substrate are defective, further exposure may be performed only on those target portions that are good.

[0049] Within the metrology system MET, the metrology equipment is used to determine one or more properties of a substrate, and in particular to determine how one or more properties vary from one substrate to another or how different layers of the same substrate vary from layer to layer. The metrology equipment may be integrated into the lithography equipment LA or the lithography cell LC, or may be a stand-alone device. In order to achieve fast measurements, it is desirable to have the metrology equipment measure one or more properties in the exposed resist layer immediately after exposure. However, the latent image in the resist has low contrast - there is only a very small refractive index difference between the parts of the resist that have been exposed to the radiation and the parts of the resist that have not been exposed to the radiation - and not all metrology equipment has sufficient sensitivity for making useful measurements of the latent image. Therefore, the measurement may be made after a post-exposure bake step (PEB), which is usually the first step performed on the exposed substrate and increases the contrast between the exposed and unexposed parts of the resist. At this stage, the image in the resist may be referred to as a semi-latent image. It is also possible to measure a developed resist image—at which point the exposed or unexposed portions of the resist have been removed—or after a pattern transfer step such as etching. While the latter may limit the possibility of reworking a defective substrate, it can still provide useful information.

[0050] In order to achieve the measurement, one or more targets may be provided on the substrate. In an embodiment, the target is specially designed and may include a periodic structure. In an embodiment, the target is a part of a device pattern, for example, a periodic structure of the device pattern. In an embodiment, the device pattern is a periodic structure of a memory device (e.g., a bipolar transistor (BPT), a bit line contact (BLC), etc.).

[0051] Figure 3 Schematically illustrating, for example, Figure 1 The measurement and exposure process of the equipment, Figure 1 The equipment includes Figure 1 200, a new substrate W' is loaded into the apparatus by a mechanism not shown in the figure. The two substrates are processed in parallel in order to increase the throughput of the lithography apparatus.

[0052] Reference is initially made to a newly loaded substrate W', which may be a previously unprocessed substrate, which has been prepared using a new photoresist for a first exposure in the apparatus. Typically, however, the lithographic process described will be only one step in a series of exposure and processing steps, so that the substrate W' has passed through this apparatus and / or other lithographic apparatus several times and may also have undergone subsequent processes. In particular for the purpose of improving overlay performance, the task is to ensure that the new pattern is applied to the correct position on a substrate that has been subjected to one or more cycles of patterning and processing. These processing steps gradually introduce distortions in the substrate, which can be measured and corrected to achieve satisfactory overlay performance.

[0053] Previous and / or subsequent patterning steps (as just mentioned) may be performed in other lithographic equipment, and may even be performed in different types of lithographic equipment. For example, some layers in the device manufacturing process that are extremely demanding in parameters such as resolution and overlay accuracy may be performed in more advanced lithographic tools than other layers that are less demanding. Thus, some layers may be exposed in immersion lithographic tools, while other layers are exposed in "dry" tools. Some layers may be exposed in tools operating at DUV wavelengths, while other layers are exposed using EUV wavelength radiation.

[0054] At 202, alignment measurements using substrate marks P1 etc. and an image sensor (not shown) are used to measure and record the alignment of the substrate relative to the substrate table WTa / WTb. In addition, an alignment sensor AS will be used to measure a number of alignment marks across the substrate W'. In one embodiment, these measurements are used to establish a "wafer grid" that very accurately maps the distribution of the marks across the substrate, including any distortion relative to the nominal rectangular grid.

[0055] At step 204, a level sensor LS is also used to measure a wafer height (Z) map relative to the XY position. Typically, the height map is only used to achieve accurate focus of the exposed pattern. The height map may additionally be used for other purposes.

[0056] When the substrate W' is loaded, the recipe data 206 is received, which defines the exposure to be performed and also defines the properties of the wafer and the previously generated pattern and the pattern to be generated on the wafer. These recipe data are added to the measurements of the wafer position, wafer grid and height map obtained at 202, 204, and the complete set of recipe and measurement data 208 can then be passed to the exposure station EXP. The measurements of the alignment data include, for example, the X position and Y position of the alignment target formed in a fixed or nominally fixed relationship with the product pattern that is the product of the lithography process. These alignment data obtained just before the exposure are used to generate an alignment model, which has parameters that fit the model to the data. These parameters and the alignment model will be used during the exposure operation to correct the position of the pattern applied in the current lithography step. When used, the model interpolates the position deviations between the measured positions. Conventional alignment models may include four, five or six parameters, which together define the translation, rotation and scaling of the "ideal" grid at different sizes. Advanced models using more parameters are known.

[0057] At 210, wafers W' and W are exchanged so that the substrate W' being measured becomes the substrate W entering the exposure station EXP. Figure 1 In the exemplary apparatus of , this exchange is performed by exchanging supports WTa and WTb within the apparatus so that the substrates W, W' remain accurately clamped and positioned on those supports to maintain the relative alignment between the substrate table and the substrate itself. Therefore, once the tables have been exchanged, determining the relative position between the projection system PS and the substrate table WTb (formerly WTa) is necessary to utilize the measurement information 202, 204 for the substrate W (formerly W') to control the exposure steps. At step 212, reticle alignment is performed using the mask alignment marks M1, M2. In steps 214, 216, 218, scanning movements and radiation pulses are applied at successive target locations across the substrate W to complete the exposure of multiple patterns.

[0058] By using the alignment data and height map obtained at the metrology station and the performance of the exposure step, these patterns are accurately aligned relative to the desired locations, in particular, relative to features previously placed on the same substrate. The exposed substrate, now marked as W", is removed from the apparatus at step 220 to undergo etching or other processes according to the exposed patterns.

[0059] Those skilled in the art will appreciate that the above description is a simplified overview of the many very detailed steps involved in one example of a real manufacturing situation. For example, rather than measuring the alignment in a single pass, there will often be separate stages of coarse and fine measurements using the same or different markers. The coarse alignment measurement step and / or the fine alignment measurement step may be performed before or after the height measurement, or may be interleaved.

[0060] In one embodiment, an optical position sensor such as alignment sensor AS uses visible light and / or near infrared (NIR) radiation to read alignment marks. In some processes, processing of layers on the substrate after alignment marks have been formed results in situations where the marks cannot be found by such alignment sensors due to low or no signal strength.

[0061] A key performance parameter of the photolithography process is the overlay error. This error, often simply referred to as "overlay," is the error in placing product features in the correct location relative to features formed in the previous layer. As product features become much smaller, overlay specifications become increasingly tighter.

[0062] Currently, for example, in a continuously running method, the overlay accuracy error is controlled using an exponentially weighted average of uncorrected overlay accuracy features of a limited number of sampled substrates from a previous batch to control the batch to be introduced (e.g., sampling 5 substrates out of 25 substrates). The existing method is a batch-based method, which means that all substrates in the batch to be introduced will receive the same correction. This correction is also called feedback (FB) control. The existing method (e.g., the continuously running FB method) has two assumptions: 1) the overlay accuracy variation between substrates within a batch is small, and 2) the overlay accuracy variation between time batches is slow. In other words, the overlay accuracy error changes slowly enough between different batches over a period of time so that the overlay accuracy error of a particular batch can be used to average without affecting the performance of the patterning process (e.g., overlay specifications, yield, etc.). However, as the technology node shrinks to the single-digit nanometer scale, these two assumptions become problematic. Additional overlay accuracy determination methods and overlay accuracy-based control are discussed in U.S. Patent Publication Nos. US2013230797A1, US2012008127A1, and US20180292761A1, which are incorporated herein by reference in their entirety.

[0063] In this context, the methods described herein use metrology data of all processed layers up to the current layer being patterned and context information (e.g., information related to the processing tools used in the patterning process), as well as overlay accuracy data of previous batches to predict overlay accuracy data for each substrate in a batch to be introduced. In an embodiment, the context information refers to, for example, information related to the processing tools used in the patterning process (e.g., Figure 2 and Figure 3 Information about the processing tools used.

[0064] In an embodiment, the term "data" may refer to a graph or feature when the data is represented as a 2D image across a substrate, wherein the values ​​of the data produce a specific pattern (e.g., feature) associated with the data. For example, overlay accuracy data associated with a layer (or substrate) may also be referred to as an overlay feature, wherein the magnitude and direction of the overlay accuracy values ​​when plotted at the substrate level produce a specific pattern (or distribution). In an embodiment, the term "data" may also refer to a pixelated image, wherein the intensity value of each pixel is associated with the value of the represented data (e.g., overlay, measurement, alignment, etc.). Specifically, depending on the type of model being trained, the data may be configured or converted into an appropriate form to be processed by the model. Figure 4A and Figure 4B In the example described in, a convolutional neural network (CNN) model is used, but the present disclosure does not limit the model to a specific model type. In addition, based on the data used to determine the model, the model can be referred to as a point level model or a substrate level model. Each model and the corresponding training process are discussed in detail in this specification.

[0065] Figure 4A An exemplary model configured to predict uncorrected overlay accuracy data (or features) for a current layer of a patterned substrate is described. In the present example, the model is a machine learning model (e.g., CNN) comprising several layers L1, L2, ..., Ln. Each layer is associated with a model parameter (e.g., a weight for each layer). For example, the first layer L1 is characterized by weights w11, w12, w13, ..., w1n. In an embodiment, the training process involves iteratively modifying the weights of one or more layers so that the predicted uncorrected overlay accuracy data (or its image) is as close as possible to the true image of the substrate (e.g., an image of the uncorrected measured overlay accuracy data). The training of the exemplary CNN model is based on a set of certain training data and a cost function described herein (e.g., see the training of Figure 7 The methods and Figure 4B Detailed description of the example).

[0066] In this example, the training of the CNN model is based on sets DS1 and DS2 of input data. The set DS1 of training data includes, for example, data related to one or more previous layers and / or the current layer of the current substrate being patterned. The set DS2 of training data includes, for example, data related to one or more previous substrates patterned before the current substrate.

[0067] In an embodiment, for example, a CNN model can be configured to directly take a substrate map or a portion of a substrate map (i.e., a die or field) as an image input, whereas other machine learning models typically convert the map into other low-dimensional representations. For example, the dimension refers to the dimension of the data set used to train the model. In an example, the low-dimensional representation refers to a reduced number of data points obtained by reducing the set of original data. For example, the set of original data may include 3000 points, which can be reduced to 10 data points, for example, via principal component analysis.

[0068] In an embodiment, the set of exemplary data DS1 may include overlay accuracy measurement data associated with a previous layer for the current substrate. The overlay accuracy measurement data includes, but is not limited to, measured overlay accuracy data (or graph) and uncorrected overlay accuracy data (or graph). In an embodiment, the measured overlay accuracy data refers to data obtained after corrections related to overlay accuracy (e.g., alignment control, level control, focus control, etc.) are applied, for example, via a patterning device. In an embodiment, the uncorrected overlay accuracy data refers to overlay accuracy data before any overlay accuracy correction is applied, for example, via a patterning device. In an embodiment, the overlay accuracy data may be obtained via, for example, optical measurement (see Figures 19 to 22 ) or SEM (see Fig.17 and Fig.18 ) to obtain overlay accuracy measurement data. In an embodiment, the overlay accuracy measurement data can be derived based on processing parameters, such as discussed in U.S. Patent Application No. 62 / 462,201 filed on February 22, 2017, which is incorporated herein by reference in its entirety.

[0069] Additionally, exemplary data set DS1 may include alignment metrology data from previous layers for the current substrate (e.g., Figure 4A alignment measurement data in the figure, including but not limited to alignment sensor data (not shown), residual map (see Figure 4A ), substrate quality map (see Figure 4A ) and / or color difference maps (see Figure 4A ).

[0070] Additionally, the exemplary data set DS1 may include leveling metrology data from a previous layer for the current substrate (eg, Figure 4A ), including but not limited to, from a substrate height map (not shown) and / or a Z2xy map (see Figure 4A ) data.

[0071] In addition, the exemplary data set DS1 may include background information for previous layers of the current substrate (e.g., Figure 4A, including, but not limited to: lag time associated with a process (e.g., resist development) performed within a tool (e.g., a resist development tool) (an example of a continuous variable), chuck identifier data (an example of a categorical variable), chamber identifier data (another example of a categorical variable), chamber FP data (e.g., Figure 4A EC1, EC2, ..., ECn shown in ), and / or other information that may be related to the overlay accuracy error.

[0072] In an embodiment, the exemplary data set DS2 includes overlay accuracy measurement data from a previous batch. In an example, the measurement data is represented as a graph generated based on the measurement data. For example, data from multiple substrates can be collected and a single graph can be generated by overlapping and / or averaging the data across the substrate. Figure 4A In the embodiment of the present invention, an overlay accuracy measurement data (e.g., overlay accuracy-prior) is obtained by taking an exponential moving average of overlay accuracy data associated with a previously patterned substrate. The overlay accuracy measurement data (e.g., overlay accuracy-prior) is represented as a graph or overlay feature illustrating a relatively high overlay accuracy error at the left edge compared to other portions of the substrate.

[0073] In an embodiment, the set of training data may be further extended to include data related to the scanner. Scanner data (an example of the set of first data in method 700) may include information associated with all layers of the current substrate up to and including the current layer. For different layers, the same substrate may be exposed by different scanners (e.g., referring to Figure 2 and Figure 3 discussed) and processed by different processing tools (e.g., see Figure 2 and Figure 3 Therefore, the scanner data need not be limited to only one scanner or one processing tool. Information related to all scanners and processing tools used in the patterning process can be used to train the model.

[0074] For example, scanner data includes, but is not limited to, tool information (e.g., scanner identification, chuck identification), raw measurement results (e.g., from measurement software, sensors, etc.) and key performance indicators related to overlay error, and reported metrology data (e.g., alignment data, leveling data, etc.). The set of training data may also include manufacturing-related data (also referred to as manufacturing context information), which includes, but is not limited to, processing tools (e.g., etching chambers, chemical mechanical polishing tools for polishing substrates, etc.), overlay measurement tools (e.g., Figures 11 to 14 The optical tools shown in Figures 9 and 10 SEM as shown in ), CD metrology tools (e.g., for measuring Figures 9 and 10 The apparatus may also include any tool that may include a CD of features of the SEM shown in the image), information related to the processing tool (e.g., chamber identification), raw measurement results (e.g., RF time as an example of lag time associated with processing of a substrate), reported metrology results (e.g., CD and overlay accuracy, etc.), and / or continuous and categorical variable information.

[0075] In addition, the set of training data may include derived data (e.g., based on scanner data and manufacturing context information), such as Z2xy, computed metrology maps (e.g., provided by a computational metrology tool) associated with, for example, process variables or performance indicators, scanner performance detection, chamber signatures derived using advanced decomposition algorithms (e.g., unique data patterns associated with variables (e.g., overlay, alignment, etc.) of a particular tool used in a patterning process (e.g., as discussed in U.S. Patent Application No. 62 / 462,201, filed on February 22, 2019, which is incorporated herein by reference in its entirety).

[0076] In an embodiment, SPD data refers to scanner performance detection, for example via simulation software, which determines the performance (e.g., key performance parameters) associated with a scanner used to image a given substrate. Scanner performance detection is discussed in further detail in European Patent Application No. EP19155660.4, filed on February 6, 2019, which is incorporated herein by reference in its entirety.

[0077] In an embodiment, Z2xy refers to the overlay accuracy contribution associated with the substrate height map. For example, the substrate height map can be obtained from the leveling sensor of the lithographic device. A difference can be found for the substrate height map for two pattern transfers, and then the difference can be converted into an overlay accuracy value, and thus converted into an overlay accuracy contribution. For example, the height difference can be considered as a warp or bend of the substrate and the X and / or Y displacement can be calculated using the first principle (for example, in the clamping area of ​​the substrate, the displacement can be the change in Z relative to the change in X or Y multiplied by half of the thickness of the substrate, or in the unclamped area of ​​the substrate, the displacement can be calculated using the Kirchhoff-Loew plate theory), to convert the Z height difference into an X and / or Y displacement. In an embodiment, the conversion of the height to the overlay accuracy contribution can be determined via simulation, mathematical modeling and / or experiments. Therefore, by using this substrate height information for each pattern transfer, the overlay accuracy impact caused by the focus or chuck light spot can be observed and considered. In an embodiment, this overlay accuracy contribution can be removed from the overlay accuracy map during the pre-processing step, as discussed herein. A detailed discussion of overlay accuracy contributions associated with substrate height map or other variables regarding the patterning process is provided in U.S. Patent Application No. 62 / 462,201, filed on February 22, 2017, which is incorporated herein by reference in its entirety.

[0078] In an embodiment, the training data can be preprocessed to improve the quality of the data, extract the most relevant data, remove certain data, etc., to improve predictions related to overlay accuracy. For example, different preprocessing methods can be applied to substrate maps to remove irrelevant / unwanted information or extract more useful information from different substrate maps. For example, for an overlay accuracy map (as an input or training output), the average feature map based on the chuck (or the moving average feature map based on the chuck) can be removed so that the remaining map can better capture the changes in overlay accuracy. As another example, the overlay substrate map can be modeled (for example, based on process variables or processing parameters) to obtain a correctable component of the total feature of the process variable of interest. For example, the total feature of the overlay includes overlay accuracy contributions from different process variables, each of which is added to produce a total feature. Then, the correctable (for example, capable of being corrected via alignment, leveling, etc.) overlay accuracy component included in the total overlay feature can be extracted. The same concept of modeling can be applied to other substrate maps related to alignment and leveling of the substrate. Additional examples of removing or extracting relevant data based on process variations of a patterning process are discussed in greater detail, for example, in incorporated US Patent Application No. 62 / 462,201.

[0079] Typically, the set of training data may include all information associated with the current substrate from all processed layers (including the current layer), and previous batches may be used for computed feature (cFP) modeling. In some cases, in feed-forward applications, due to scanner throughput limitations, all information, such as certain scanner information (e.g., alignment and leveling of the current layer), may not be available in a timely manner. However, as metrology-related technology improves, such data may be available in real time, in which case all real-time scanner information may also be used to train the model for more accurate predictions.

[0080] In the present disclosure, a set of training data may include all inputs (e.g., data within DS1, DS2, and measured overlay accuracy data) or any combination of inputs (e.g., data selected from DS1, data selected from DS2, etc.). For example, a set of all data mentioned herein may be used as input for building a complex machine learning model as discussed herein. As another example, one or more selected subsets of the inputs from the above list may be used to build a model (also referred to as a cFP model). The selection of one or more subsets may be based on certain features. Feature selection may be based on domain knowledge or simply based on data driven by using any existing feature selection algorithm in the field of machine learning.

[0081] Regarding output, the model can predict uncorrected overlay accuracy data based on the current layer for the current substrate, and the uncorrected overlay accuracy data is later used to control various processes of the patterning process (for example, as discussed in U.S. applications US2013230797A1 and US2012008127A1, which are incorporated herein by reference) to improve the yield of the patterning process, such as defects caused by overlay accuracy errors associated with extremely small features (for example, less than 10 nm).

[0082] As mentioned earlier, input data is used to generate predicted outputs via the model. The goal of the training process is to predict accurate output data. In an embodiment, such accurate predictions are achieved by reducing the error between the predicted output data and the underlying true (or reference data). For example, Figure 4B The difference between the predicted uncorrected overlay accuracy data PDOD (e.g., a map) and the uncorrected measured overlay accuracy data MDOD (an example of a true or reference map of the substrate) is illustrated. In this example, the predicted uncorrected overlay accuracy data PDOD is associated with the current layer of the substrate being processed. Before any correction is applied to the current layer, the model is executed using the inputs DS1 and DS2 (e.g., Figure 4A ) to obtain this prediction data PDOD. Similarly, before applying any correction to the current layer, the measurement data MDOD is obtained through the measurement tool. If the model (e.g., Figure 4A If the predictions of the CNN in ( ) are accurate, the difference DIFF should be very close to zero, and ideally zero.

[0083] Because the training process is an iterative process, the first prediction of the CNN model using the initial weights may be far from zero. However, gradually, the values ​​of the weights (e.g., w11, w12, w13, ..., w1n, ..., w nm) of the CNN model can be adjusted (e.g., using a gradient descent method) to reduce the difference DIFF. In an embodiment, the training stops when the difference DIFF is minimized. The CNN model characterized by the final weight value is then considered to be a training model. The training model can be used to predict the overlay accuracy data for any design layout printed on the current layer of the current substrate. Based on the predicted overlay accuracy data, adjustments can be made in a real-time (e.g., in high-volume manufacturing HVM) environment so that the overlay accuracy error associated with the design layout and the yield of the patterning process are improved.

[0084] In an embodiment, different cost functions may be used to train a model, resulting in an improved trained model. In this document, the cost function is independent of the model type (e.g., point level model or substrate level model). Depending on the type of model trained, appropriate transformations may be applied so that any cost function can be used with any model. For example, the transformation may be related to converting point level data to substrate level data or vice versa so that the components of the cost function are in the same units or dimensions (e.g., 1D point level or 2D graph).

[0085] In embodiments, the cost function may be: (i) a first function (CF1) or average n-order error (e.g., MSE is mean square error), (ii) a second function or average 3 standard deviations (M3S or CF2), or (iii) overlay accuracy error on a product. The cost function may be applied to both a point level model or a substrate level model, as described below with reference to Figure 7 Discussed in detail.

[0086] In an embodiment, the first function (CF1) or the mean n-th order error (or CF1) can be calculated as CF1 = mean(sum[|pred-reference|^n]), where pred is the predicted data and reference is the reference data; and mean is based on the absolute difference between the predicted data and the reference data. The predicted data and the reference data can be an overlay accuracy value associated with a given point (e.g., an overlay mark) on a given substrate, or a projection coefficient (also referred to as a basis coefficient) associated with a given substrate.

[0087] In an embodiment, a second function or mean 3 standard deviations (M3S) can be calculated as: CF2=abs(mean)+3×std, where abs(mean) is the absolute mean and 3×std is 3 times the standard deviation obtained based on the difference between predicted uncorrected overlay accuracy data and reference data, where the predicted data is the overlay accuracy value associated with a given point on a given substrate.

[0088] In an embodiment, OPO (or CF3) may be defined as: CF3 = abs(M3S) + 1.96 x std(M3S), where the mean and standard deviation of M3S are calculated using predicted data as overlay values ​​associated with a given series of substrates.

[0089] Figure 5Exemplary point level data for training point level models is described. In embodiments, the point level model may be Model 1 and / or Model 2, wherein Model 1 (e.g., cFPx model) may be configured to predict uncorrected overlay features in the x-direction, and Model 2 (e.g., cFPy model) may be configured to predict uncorrected overlay features in the y-direction. In embodiments, a single model may be determined that predicts overlay accuracy in both the x- and y-directions.

[0090] exist Figure 5 In the example, each measured mark on the substrate becomes a data sample source that provides multiple measurement values ​​(provided in the charts such as overlay accuracy, alignment, adjustment, etc.) at a given position in one of the previous layers for the current substrate, as discussed herein. For example, a location P1 corresponding to an overlay mark is associated with different data elements such as chuck identification, measured overlay accuracy, uncorrected overlay accuracy, alignment system residual, and alignment quality. In this exemplary chart, the measured overlay accuracy measure_ovl (e.g., via e.g. Figures 19 to 22 The overlay of the previous layer (e.g., layer 1) of the substrate in the x-direction and the y-direction is captured by the metrology tool in the process. The uncorrected overlay accuracy DCOv1 is for the previous layer of the current substrate being patterned. The DCOv1 data can be obtained from the metrology tool and further used as a training tool for the model (e.g., Figure 4A The alignment system residual may include residual alignment values ​​obtained via different color lasers used by the alignment system. Furthermore, an inter-color map may be obtained based on the difference in diffraction patterns obtained from different color lasers. A similar set of information may be obtained for other previous layers (e.g., layers 2 to 4).

[0091] In this example, a training data sample or data element at P1 ( Figure 5 ) has 81 dimensions (e.g., 20×4+1), where 20 data values ​​come from the measured overlay accuracy, uncorrected overlay accuracy, alignment system residuals, and alignment quality features for a layer; 4 is the number of previous layers for a given substrate, and 1 refers to the chuck identification. Therefore, P1 provides a data sample that includes 81 dimensions (or data values) to predict an overlay accuracy value. If this substrate has 300 markings, the training data will include 300 such data samples or 300×81 data values.

[0092] In an embodiment, training a point level model (e.g., based on point level data) may involve aligning grids of substrate maps from different metrology tools and also from different layers. This alignment of the grids may be performed via modeling and interpolation of the data relative to a common grid. In an embodiment, substrate level information (e.g., chuck identification, RF time, etc.) is shared (i.e., the same) for all points within the substrate. The point level model may use all information available at position P1 to predict the overlay accuracy value at position P1. Although this approach can help amplify the amount of data, it may be overly simplified because it processes all points independently.

[0093] In an embodiment, the point level model may be trained based on any of the cost functions described herein.For example, the cost function may be a first function of order 2 also known as mean square error (MSE) used to determine the values ​​of model parameters characterizing the point level model.

[0094] In an embodiment, one skilled in the art may use point level data to predict an overlay substrate map based on a data set associated with each given point on a given substrate. The predicted overlay accuracy map may be projected to a set of basis functions (e.g., linear, quadratic, Zernike polynomials, etc.) to obtain projection coefficients (or basis coefficients). The projection coefficients may be used to calculate a cost function based on the difference between the predicted coefficients and the true coefficients of the substrate, wherein the true coefficients of the substrate are obtained by projecting the uncorrected measured overlay accuracy data to the same set of basis functions. This model fitting calculation is differentiable and can therefore be optimized using, for example, a standard gradient-based method.

[0095] In another example, where a set of training data at the substrate level (e.g., the entire substrate, relative to a single point on the substrate) is presented, the training model may be referred to as a substrate level model (not illustrated). In an embodiment, a given substrate may be associated with multiple substrate maps, such as, for example, an alignment map, a leveling map, and / or a measured overlay accuracy map. In the substrate level model, each substrate becomes a data sample source, wherein each associated map (e.g., an alignment map, a leveling map, an overlay accuracy map, etc.) is projected onto a set of basis functions to obtain its coefficients as a numerical representation for the projection map. In an embodiment, the projection map may be used as an input or output for a substrate level model. In an embodiment, the basis function may be a principal component analysis basis function, a Zernike polynomial, or other more complex overlay models including basis functions that include both inter-field function components and intra-field function components. In an embodiment, substrate level information (e.g., chuck identification, RF time, etc.) may also be encoded and then used as an additional input for determining the substrate level model. Again, any cost function discussed above may be used to determine the values ​​of model parameters associated with the substrate level model.

[0096] For example, the cost function can be an overprint on product (OPO). To determine the OPO, a set of projection coefficients is first determined by applying a substrate level model using input data associated with the current substrate of interest (in an appropriate format). An overprint accuracy map can then be reconstructed based on the predicted coefficients. A cost function can then be calculated, for example, based on the difference between the reconstructed overprint accuracy map and the substrate true map. Additionally, a standard gradient-based approach can be used to determine the optimized values ​​of the cFP model parameters that yield the best prediction results (e.g., very close to or identical to the substrate true map).

[0097] In an embodiment, projection of each of a plurality of substrate maps may be performed to reduce the dimension of the data. For example, for a substrate, there are a plurality of substrate maps (e.g., overlay accuracy maps, alignment maps, leveling maps, etc.) and each substrate map includes a plurality of data points (e.g., 300). Then, for example, assuming that there are 10 substrate maps, each of which has 300 data points, the total dimension of the data will be 3000. Therefore, in order to reduce the dimension, each substrate map may be reconfigured using a basis function (e.g., PCA), resulting in projection coefficients associated with each projection map. Such projection maps may be generated for certain substrate level models, where a collection of data that handles high dimensions may be computationally intensive. However, the present disclosure does not limit substrate models determined based on projection coefficients. For example, a convolutional neural network may be able to handle images (e.g., substrate maps), in which case projection of data on basis functions may not be performed.

[0098] Figure 6 An example in which the decomposition of the OVL graph is performed based on basis functions related to both the inter-field component and the intra-field component is described. Figure 6 The exemplary overlay accuracy map OVL map in can be decomposed into a B-in map and a B-between map. Each map is associated with certain coefficients determined via a decomposition method such as PCA, linear regression or other known methods. The above example is further explained in the following method.

[0099] Figure 7 is a flow chart of a method 700 for determining a model used to predict uncorrected overlay accuracy data associated with a current substrate being patterned. The method 700 involves several processes as discussed in detail below.

[0100] Process P701 involves obtaining (i) a set 701 of first data associated with one or more previous layers and / or a current layer of a current substrate being patterned, (ii) a set 702 of second data comprising overlay accuracy measurement data associated with one or more previous substrates patterned prior to the current substrate, and (iii) uncorrected measured overlay accuracy data 703 associated with a current layer of the current substrate.

[0101] In an embodiment, the set of first data 701 also includes scanner data associated with one or more scanners used to pattern one or more previous layers and / or the current layer of the current substrate; and manufacturing context data associated with processing tools to which the current substrate was subjected before the current layer was patterned or to which the current layer will be subjected after the current layer is patterned. For different layers, the same substrate may be exposed by different scanners and processed by different processing tools, for example, referring to Figure 2 and Figure 3 Therefore, data need not be associated with only one scanner or one processing tool.

[0102] In an embodiment, the scanner data includes one or more of the following: a scanner identifier and a scanner chuck identifier associated with one or more scanners; measurements calculated via sensors or measurement systems of one or more scanners; one or more key performance indicators associated with one or more scanners and related to the overlay accuracy of the current substrate; and measurement data obtained from alignment sensors, leveling sensors, height sensors, and / or other sensors operably connected to one or more scanners. In an embodiment, the tools used in manufacturing include one or more of an etching chamber, a chemical mechanical polishing tool, an overlay accuracy measurement tool, and / or a CD measurement tool. In an embodiment, an overlay accuracy measurement tool, such as an optical tool (e.g., Figures 11 to 14 ), SEM (e.g. Figures 9 and 10 ) or other tools configured to measure overlay accuracy. In embodiments, a CD metrology tool, such as a SEM or other tool may be used to determine the CD of a feature. Figure 2 and Figure 3 Additional tools are further discussed in and in U.S. patent application 62 / 834,618 filed on April 16, 2019.

[0103] In an embodiment, a set 701 of first data (e.g., Figure 4A and Figure 5 ) includes overlay accuracy measurement data of one or more previous layers and / or the current layer of the current substrate (e.g., Figure 4A The overlay accuracy measurement data may include: (i) measured overlay accuracy data obtained after applying an overlay accuracy correction to one or more previous layers of a current substrate, and / or (ii) uncorrected overlay accuracy data obtained before applying an overlay accuracy correction to one or more previous layers of a current substrate.

[0104] In an embodiment, the set of first data 701 includes alignment metrology data of one or more previous layers and / or current layers of the current substrate (eg, Figure 4A The alignment metrology data may include: (i) alignment sensor data, (ii) a residual map generated by an alignment system model, (iii) a substrate quality map including signals with varying intensities indicating the reliability of the alignment data, and / or (iv) a color-to-color difference map obtained by projecting multiple color laser beams onto a substrate (e.g., reference Figure 4A As discussed above, each color laser beam is reflected from an alignment mark on one or more previous layers, and the reflected beam produces a diffraction pattern, the color difference map being the difference between a first diffraction pattern and a second diffraction pattern, the first diffraction pattern being obtained using a first color among a plurality of color lasers, and the second diffraction pattern being obtained using a second color among a plurality of color lasers.

[0105] In an embodiment, the set of first data 701 includes leveling metrology data of one or more previous layers and / or the current layer of the current substrate (eg, Figure 4A The leveling measurement data in the embodiment of the present invention may include: (i) substrate height data, and / or (ii) substrate height data converted into displacements in the x and y directions.

[0106] In an embodiment, the set 701 of first data includes manufacturing context information of one or more previous layers and / or the current layer of the current substrate, the context information including: (i) a lag time associated with a process of a patterning process (e.g., discussed earlier), (ii) a chuck identifier on which the current substrate is mounted, (iii) a chamber identifier indicating a chamber in which the process of the patterning process is performed, and / or (iv) chamber characteristics characterizing an overlay accuracy contribution of one or more processing parameters associated with the chamber (e.g., leveling, alignment, etch rate, etc.). In an embodiment, the lag time may be associated with a process or a metrology tool used in the process. Exemplary lag times may be associated with resist development, time required to obtain an overlay accuracy measurement, implementation of a control command, etc.

[0107] In an embodiment, the set 701 of first data also includes derived data associated with parameters of the patterning process that contribute to overlay accuracy, wherein the derived data is derived from scanner data and / or manufacturing context information. For example, the derived data may be obtained as discussed in the previously mentioned U.S. patent application 62 / 462,201; U.S. patent application 62 / 834,618 filed on April 16, 2019; or European patent application No. EP19155660.4 filed on February 6, 2019.

[0108] Step P703 involves determining values ​​of a set of model parameters associated with a model based on (i) a set of first data 701, (ii) a set of second data 702, and (iii) measured data 703, so that the model predicts uncorrected overlay accuracy data for the current substrate. In an embodiment, the values ​​of the model parameters are determined to minimize a cost function that includes the difference between the predicted data and the measured data 703.

[0109] In an embodiment, reducing the cost function is an iterative process. For example, in step P705, a determination is made as to whether the cost function is reduced. If the cost function is not reduced, the values ​​of the model parameters (e.g., weights and biases of a CNN, or parameters associated with a mathematical function) are determined again or the existing values ​​of the model parameters are adjusted (e.g., based on a gradient-based method) so that the model prediction output is close to the data of the measured data 703. In an embodiment, iterations continue until the cost function is minimized. For example, the cost function value exceeds a desired threshold (e.g., zero, a pre-selected value, or a value determined via a gradient method). Once step P705 determines that the cost function is minimized or that further improvement of the cost function is not achieved by modifying the values ​​of the model parameters, the training process stops. In an embodiment, the training process may stop after a predetermined number of iterations. At the end of the training process, a training model 705 with determined values ​​of the model parameters is obtained.

[0110] In an embodiment, the model is configured to predict uncorrected overlay accuracy data at a point level for a current substrate, where a point is a location on the substrate where an overlay mark is formed on the current substrate.

[0111] In an embodiment, the model is a point level model, wherein values ​​of model parameters of the point level model are determined based on a set 701 of first data, a set 702 of second data, and uncorrected measured overlay accuracy data 703 obtained at a given location on a current substrate having overlay marks.

[0112] In an embodiment, the process of obtaining a set of first data 701, a set of second data 702, and a set of uncorrected measured overlay accuracy data 703 at a given location on a current substrate having overlay marks includes: representing the values ​​of the set of first data 701, the set of second data 702, and the uncorrected measured overlay accuracy data 703 in the form of a substrate map; aligning each of the substrate maps via modeling and / or interpolation; uniformly sharing substrate level information within the set of first data, the set of second data, and the uncorrected measured overlay accuracy data, respectively, over the entire current substrate; and extracting the values ​​of the set of first data, the set of second data, and the uncorrected measured overlay accuracy data, respectively, that are associated with the given location.

[0113] In an embodiment, the substrate level information includes at least one of: a chuck identifier, and / or a lag time associated with a processing tool used in a patterning process of the current substrate.

[0114] As mentioned earlier, the model can be configured to predict uncorrected overlay accuracy data at substrate level. Therefore, the model is referred to as a substrate level model. In an embodiment, the values ​​of the model parameters of the substrate level model are determined based on the projection coefficients associated with the set of first data 701, the set of second data 702 and the graph of uncorrected measured overlay accuracy data 703 over the entire substrate.

[0115] In an embodiment, the process of determining the values ​​of the model parameters of the substrate model also includes: generating a plurality of substrate maps using the values ​​of the set 701 of first data associated with a plurality of previous substrates, the set 702 of second data, and the uncorrected measured overlay accuracy data 703, respectively; projecting each of the plurality of substrate maps onto a basis function (e.g., PCA, Zernike, or composite intra-field and inter-field functions, as discussed earlier); determining projection coefficients associated with the basis function based on the projection, the projection coefficients being used to define the substrate model. For example, the projection coefficients may be used as input and / or output so that an appropriate cost function (e.g., OPO) may be calculated. For example, the input may be projection coefficients associated with a plurality of substrate maps, and the reference coefficients may be obtained via the projection of the measured overlay accuracy data 703 onto the basis function. Then, based on a cost function associated with the projection coefficients (e.g., the mean square error of the absolute difference between the predicted projection coefficients and the reference coefficients), the values ​​of the model parameters may be determined.

[0116] In an embodiment, the processing of projecting the substrate map onto the basis functions comprises: performing principal component analysis; or performing a single value decomposition of the substrate map. In an embodiment, the basis functions are a set of Zernike polynomials, and the model parameters are Zernike coefficients, each Zernike coefficient being associated with a corresponding Zernike polynomial of the set of Zernike polynomials.

[0117] As mentioned earlier, projecting the substrate map onto the basis functions can be performed to reduce the dimensionality of the sets of training data 701, 702, and 703. However, when using a CNN model, the projection step can be omitted and the original data 701, 702, and 703 can be used for training the CNN model.

[0118] In an embodiment, the model is at least one of the following: a linear model or a machine learning model. In an embodiment, the linear model is determined based on: (i) a set of first data associated with at least one selected layer of the current substrate or at least one selected layer of the previous substrate, or (ii) a set of first data associated with multiple layers of the current substrate or the previous substrate. In an embodiment, the selected layer can be selected based on the overlay accuracy contribution from the layer, the key features on the layer, or other overlay accuracy related factors. For example, the layer that captures the maximum overlay accuracy contribution, or the layer with the most critical features compared to other layers of a given substrate. For example, for a linear model, different inputs can be: 1) the uncorrected overlay accuracy of one most important previous layer, 2) the uncorrected overlay accuracy of N selected previous layers of the substrate (e.g., such as the N most important layers with critical features), and / or 3) all available input information from both 1 and / or 2. When data from multiple layers are used, the associated feedforward control can be referred to as multi-layer feedforward. In other words, multi-layer feed-forward implies that the control of the patterning process is based on the overlay accuracy based on multiple layer predictions, thereby capturing more sources of variation, which in turn will lead to improved control determination.

[0119] In an embodiment, the machine learning model may include multiple model layers, each model layer is associated with weights and / or biases, and the weights and biases are model parameters. In an embodiment, the machine learning model is at least one of the following: a multilayer perceptron; a random forest; an adaptive boosting tree; support vector regression; a Gaussian process regression; and / or a k-nearest neighbor algorithm.

[0120] In an embodiment, the machine learning model is an advanced machine learning model including at least one of the following: a residual neural network (RNN); or a convolutional neural network (CNN). In an embodiment, the RNN model is formulated to include a previous layer of a current substrate or a previous substrate as a time axis of the RNN.

[0121] In an embodiment, for a CNN model, the set of training data may be the same as before, and the set of training data may include a set of first data 701 and a set of second data 702. In addition, the output may be an uncorrected overlay accuracy map. However, currently, a CNN model may directly use a substrate map or a portion of a substrate map (i.e., a die or field) as an image input, whereas typically for other machine learning models, a set of raw data may need to be converted into other low-dimensional representations (e.g., via PCA).

[0122] For example, a CNN is trained based on images associated with a current substrate or a portion of a current substrate and / or images associated with one or more previous substrates, wherein the images include predicted images representing predicted uncorrected overlay accuracy data and measured images representing measured overlay accuracy data. For illustration, non-image data may also be used as additional input to train the CNN. For example, the set of training data may include chuck identification, chamber identification, lag time, or other similar inputs.

[0123] As mentioned earlier, the present method 700 may use any cost function to determine the values ​​of the model parameters. The cost function is not limited to a particular model (eg, a point level model or a substrate model) or model type (eg, linear, CNN, etc.).

[0124] In an embodiment, the cost function is at least one of: a first function, a second function (M3S), or an overlay on a product. Figure 4A and Figure 4B Exemplary equations are discussed.

[0125] In an embodiment, a first function (wherein the first average error is an nth order error) is calculated using the absolute difference between predicted data and reference data and raising the difference to the nth order, wherein the predicted data is an overlay accuracy value associated with a given point on a given substrate or a projection coefficient associated with a given substrate, and the reference data.

[0126] In an embodiment, the second function (M3S) is calculated using the sum of the absolute value of the mean and three times the standard deviation, wherein the mean and the standard deviation are obtained based on the difference between the predicted uncorrected overlay accuracy data and the reference data, the predicted data being the overlay accuracy value associated with a given point on a given substrate. For example, if there are 10 substrates, the mean and the standard deviation are calculated using data associated with the 10 substrates.

[0127] In an embodiment, the on-product overlay accuracy is calculated using the sum of the mean value of M3S and 1.96 times the standard deviation of the M3S, where the mean value and standard deviation of M3S are calculated using predicted data as overlay accuracy values ​​associated with a series of given substrates. The value 1.96 does not limit the scope of the present disclosure. In another example, other values ​​besides 1.96 may be used to determine OPO.

[0128] It should be noted that the second function and the OPO are based on point level data. Therefore, when projection coefficients are available, such as in the case of a substrate model, the projection coefficients must be used to reconstruct a substrate map, and then point level data can be extracted from such substrate map to determine the second function and the OPO.

[0129] The cost function is minimized using a gradient-based method. Such methods are well known and their implementation details are omitted for brevity.

[0130] The use of the above cost function can be explained, for example, in conjunction with steps P703 and P705 for determining a point-level model. These steps include: using data associated with each given location in a plurality of locations on a current substrate, executing the point-level model using initial model parameter values ​​to predict uncorrected overlay accuracy data; and determining values ​​of the model parameters based on the predicted uncorrected overlay accuracy data and metrology data at the plurality of locations so that the first function, the second function, and / or the on-product overlay accuracy associated with each given location in a plurality of locations on a given substrate are minimized.

[0131] In an embodiment, determining a point-level model involves first predicting a de-corrected overlay accuracy map point-by-point using the point-level model, then projecting the substrate map onto some substrate to obtain coefficients, and finally calculating a cost function based on the projection coefficients (e.g., the difference between the projection coefficients associated with the predicted map and the projection coefficients associated with a reference map (e.g., measured overlay accuracy data)) using, for example, MSE.

[0132] In another example, the substrate model may be characterized by projection coefficients. In this case, steps P703 and P705 of determining the substrate level model may include: predicting projection coefficients associated with the basis functions using the substrate model; constructing an overlay accuracy map based on the predicted projection coefficients; calculating a second function or an overlay accuracy on the product based on a difference between the constructed overlay accuracy map and a reference overlay accuracy map (e.g., a measured overlay accuracy map); and determining values ​​of the model parameters such that the second function or the overlay accuracy on the product is minimized.

[0133] In other words, in an embodiment, the output of the substrate level model (e.g., non-CNN) is the projection coefficients, which can be used directly to determine the cost function. For example, according to one method, we first use the substrate model to predict the projection coefficients. Then, the cost function is calculated based on the predicted projection coefficients. If the cost function is a first function (e.g., MSE) based on the predicted coefficients and reference coefficients (e.g., obtained by projecting measurement data), the cost function is a simple calculation. However, if the cost function (e.g., MSE, M3S, OPO) is based on the predicted overlay accuracy map and the point values ​​of the reference map, the substrate map must be reconstructed using the predicted coefficients and the reference coefficients (i.e., the reverse projection process).

[0134] As mentioned earlier, such projection coefficients are determined to reduce the dimensionality of the training data. However, the entire data set or a portion of the data set (e.g., one or more dies, fields, or selected areas of a substrate) may be used to train a model (e.g., a CNN model) without performing the projection step.

[0135] As discussed in the present disclosure, the cost function can be used to train a substrate model or a point level model. Depending on the type of data used to train the model, appropriate data transformations can be applied so that any cost function can be used with any model. For example, the transformation (e.g., via projecting the data onto a basis function) can include converting point level data into substrate level data or vice versa so that the components of the cost function are in the same units or dimensions (e.g., 1D point level or 2D graph).

[0136] As mentioned earlier, in an embodiment, the set of first data, the set of second data, and the uncorrected measured overlay accuracy data are preprocessed to extract desired information from the corresponding sets of data. For example, the sets of data 701, 702, and 703 can be preprocessed to extract, for example, alignment system model residual data; leveling related residual data; and / or correctable overlay accuracy error data. Examples of preprocessing data are discussed in detail in U.S. Patent Application No. 62 / 462,201. Therefore, such methods can supplement data processing to improve data quality and thereby improve the resulting training model.

[0137] In an embodiment, the set of first data 701 or the set of second data 702 may be incomplete (e.g., some data is missing due to measurement constraints). For example, in an embodiment, the set of data 701 or 702 may have some missing overlay accuracy measurement data and / or missing background data associated with one or more previous substrates or one or more previous layers of the current substrate.

[0138] In an embodiment, the missing overlay accuracy data is replaced by average overlay accuracy data, wherein the average overlay accuracy data is calculated based on a batch (or group) of substrates or based on a grouping of substrates based on background data. In an example, the grouping can be based on a grouping method such as k nearest means. Based on the grouping method, a group of identifiers can be assigned to each substrate to be introduced and the average overlay accuracy data of each group can be determined.

[0139] In an embodiment, the missing overlay accuracy data is replaced by overlay accuracy data based on domain knowledge, wherein the domain knowledge based overlay accuracy data is generated using computational metrology, wherein the computational metrology includes an overlay accuracy prediction model based on parameters of the patterning process.

[0140] In an embodiment, a model (e.g., a point level model or a substrate level model) can be structured as a two-level hierarchical model. In an embodiment, a first level of the hierarchical model is configured to predict overlay accuracy data using inputs that always exist including data in a set of first data and a set of second data, and a second level of the hierarchical model predicts an improvement in overlay accuracy of the predicted overlay accuracy data of the first level based on inputs that do not always exist, the inputs including overlay accuracy and certain background data. In an embodiment, for a substrate with all inputs that exist, the sum of the predictions from the two levels is used as the final result. For substrates with missing overlay accuracy data, the second level prediction is skipped. In an embodiment, method 700 further involves jointly optimizing the two levels of the hierarchical model.

[0141] Step P709 involves determining an overlay accuracy correction 709 or control parameter 709' associated with the lithographic apparatus based on the predicted uncorrected overlay accuracy data 707 to improve the overlay performance of the lithographic apparatus. The predicted uncorrected overlay accuracy data 707 may be obtained using inputs related to a current layer of a current substrate being processed as an output of executing the training model 705. In an embodiment, the predicted overlay accuracy data 707 may be provided as a Figure 3 In an embodiment, the predicted data 707 may be provided to a correction model such as that described in 2013230797A1. Since the training model according to the present invention may provide more accurate overlay predictions, the resulting corrections (e.g., for reducing overlay precision errors) will be more accurate, thereby improving the prior art.

[0142] Figure 8 8 is a flow chart of a method for updating a training model used to predict uncorrected overlay accuracy data associated with a current substrate being patterned. In an embodiment, the real-time update may involve obtaining a set 801 of real-time data. In an embodiment, the set 801 of real-time data is similar to the sets 701, 702, and 703 of data discussed earlier. For example, the set 801 of real-time data is related to similar processing parameters, such as the scanner data and background data discussed earlier, as long as the data is real-time, such as data obtained within a time window relative to the current time.

[0143] In step P801, method 800 includes obtaining (i) a set of first data associated with one or more previous layers of a current substrate being patterned, (ii) a set of second data including overlay accuracy measurement data associated with one or more previous substrates patterned prior to the current substrate, and (iii) uncorrected measured overlay accuracy data associated with the current substrate.

[0144] In step P803, method 800 involves updating training model 705 based on a set of first data, a set of second data, and uncorrected measured overlay accuracy data associated with the current substrate, such that a cost function associated with the training model decreases. In an embodiment, the cost function includes a difference between predicted uncorrected overlay accuracy data and the uncorrected measured overlay accuracy data, the predicted data being obtained by executing the training model using the set of first data and the set of second data.

[0145] In an embodiment, updating the training model 705 based on the cost function is an iterative process involving step P805 (similar to step P705 discussed earlier). The iterative process includes determining the value of the cost function and updating the values ​​of the model parameters so that the cost function is reduced or minimized. The cost function used to update the training model 805 can be the same as discussed earlier. For example, the cost function can be a first function, a second function, and OPO.

[0146] In an embodiment, the real-time data 801 may include missing data including missing overlay accuracy metrology data and / or missing background data associated with, for example, one or more previous layers or a current layer of a current substrate.

[0147] In an embodiment, the missing overlay accuracy data is replaced by average overlay accuracy data, wherein the average overlay accuracy data is calculated based on a batch (or group) of substrates or based on grouping of substrates based on background data. In an example, the grouping can be based on a grouping method such as k nearest means. Based on the grouping method, a group of identifiers can be assigned to each substrate to be introduced and then the average value of each group can be determined.

[0148] In an embodiment, missing overlay accuracy data is replaced by overlay accuracy data based on domain knowledge, wherein the domain knowledge based overlay accuracy data is generated using computational metrology, wherein the computational metrology includes an overlay accuracy prediction model based on parameters of the patterning process.

[0149] In an embodiment, a training model (e.g., a point level model or a substrate level model) can be structured as a two-level hierarchical model. In an embodiment, a first level of the hierarchical model is configured to predict overlay accuracy data using inputs that always exist including data in a set of first data and a set of second data, and a second level of the hierarchical model predicts an improvement in overlay accuracy of the predicted overlay accuracy data of the first level based on inputs that do not always exist, the inputs including overlay accuracy and certain background data. In an embodiment, for a substrate with all inputs that exist, the sum of the predictions from the two levels is used as the final result. For wafers with missing overlays, the second level prediction is skipped. In an embodiment, method 800 also includes jointly optimizing the two levels of the hierarchical model.

[0150] As mentioned earlier, currently, overlay control is based on an index-weighted moving average (EWMA) approach, where the measurements of the previous batch are combined in a weighted average manner and then applied to the next batch: this is a feedback control loop. In the overlay run-to-run (R2R) control approach, there are two main contributors to overlay error: scanner effect and process effect, among other contributors. The scanner contribution changes slowly with respect to process variations. Because process variations have a high frequency, applying process corrections from a previous batch to the next batch may not be a good approach for advanced node wafer manufacturing applications and may cause overlay errors to be out of specification.

[0151] In this article, refer to Fig. 9 Instead of applying the overlay characteristics determined based on EWMA to the next batch, it is proposed to separate the slowly varying signals (e.g., contributions from the scanner) from the high frequency signals (e.g., from process variations between wafers). The slowly varying parts from the historical batches can then be combined with the high frequency contributions of the wafers to be exposed in the current batch to be used as a new correction for the wafers of the current batch. In an example, the process contribution of each wafer can be estimated using a model of the current substrate and the alignment signal. In an example, the machine learning model for determining the process contribution to overlay can be based on various extracted KPIs, such as based on the PCA score between the alignment KPI and the PCA of the overlay signal. Therefore, compared to the standard EWMA R2R control (batch level control) based on the average overlay accuracy of previous batches, the method proposed in this article is a wafer level control.

[0152] An advantage of the proposed wafer level control method is that the proposed wafer level control method does not require additional overlay accuracy metrology costs compared to standard R2R control. Another aspect of the method discussed in the present disclosure is that the alignment signals from the previous layer can be used to build a model for performing overlay accuracy feed-forward correction. An advantage of this method is that all calculations can be performed outside the scanner, for example by a separate software product, and the feed-forward correction can be supplied to the scanner without modifying the existing scanner software.

[0153] exist Fig. 9 In the example in , the performance data may be overlay accuracy data obtained from a previous batch (e.g., batch 1, batch 2, ..., batch m), each batch including a plurality of wafers (e.g., n number of wafers). The performance data may be further corrected by removing process-induced overlay features from the overlay accuracy data. In an embodiment, the process-induced overlay features are identified based on, for example, a temporal analysis of previous batch data, an available processing feature library, etc.

[0154] In an example, the EWMA overlay feature or the overlay feature based on historical data may indicate that the average overlay accuracy of batch 1 is 0.5 nm. For the current batch, each wafer includes an overlay accuracy variation across the wafer due to process-induced overlay. For example, the first wafer of the current batch has an overlay accuracy value (e.g., CWP) of 0.1 nm, the second wafer has an overlay accuracy value of 0.2 nm, the third wafer has an overlay accuracy value of 0.3 nm, and the like. Then, the correction to be applied to the current wafer (e.g., the first wafer) is based on a total overlay accuracy value of 0.6 nm (i.e., 0.5+0.1). Similarly, for the second wafer, the overlay accuracy correction is based on 0.7 nm (i.e., 0.5+0.2), and the like. Therefore, each wafer in the current batch will be corrected based on different overlay accuracy values ​​based on the process-induced overlay of the historical overlay and the current wafer overlay accuracy value. In an embodiment, the overlay accuracy correction involves adjusting the lithography process so as to reduce the overlay accuracy error in the current wafer.

[0155] In an embodiment, a model (e.g., a machine learning model) is trained based on the alignment data to predict process-induced overlay features. For example, color-to-color features are modeled to historically measured overlay accuracy data to train the model.

[0156] In an embodiment, a training model is used to predict the overlay accuracy error CWP caused by a process or a tool used in the process. Then, for the current wafer CW to be exposed or patterned, the overlay accuracy error from the previous batch (e.g., batch 1) is combined with the predicted overlay accuracy error CWP for the process using the alignment data of the wafer to derive the best process correction for the current wafer CW, combining feedback (overlaying the previous batch) and feedforward (alignment of the current wafer) to derive the best overlay accuracy correction for the current wafer CW. For example, this best overlay accuracy correction results in an OPO improvement of 0.3 nm. The proposed method for overlay accuracy correction is discussed in further detail below.

[0157] Fig.10 is a flow chart of a method 900 for determining an overlay accuracy correction for a current substrate to be patterned. The method includes steps P901 to P905, for example, as discussed further below.

[0158] Process P901 includes obtaining (i) performance data 902 associated with a previously patterned substrate, and (ii) measurement data 904 associated with a current substrate to be patterned. In an embodiment, the performance data 902 includes overlay error data of the previously patterned substrate. In an embodiment, the performance data 902 is an average overlay error value obtained by averaging the overlay error values ​​associated with the previously patterned substrate. For example, the average overlay error from a previous batch may be 0.5 nm. In an embodiment, the performance data 902 is specific to each tool used in the semiconductor manufacturing process. For example, overlay data of a batch processed by the same tool (e.g., scanner, etc.) as the current batch is used.

[0159] In an embodiment, the metrology data 904 includes alignment metrology data and leveling metrology data associated with the current substrate. In an embodiment, the alignment metrology data includes: (i) alignment sensor data, (ii) a residual map generated by an alignment system model (e.g., an uncorrectable alignment map calculated as the difference between alignment and data that the scanner can correct), (iii) a substrate quality map including a signal with varying intensity indicating the reliability of the alignment data, and / or (iv) a color difference map obtained by projecting a plurality of color laser beams onto the substrate, each color laser beam being reflected from an alignment mark on a layer of the current substrate, the reflected beams generating a diffraction pattern, the color difference map being the difference between a first diffraction pattern and a second diffraction pattern, the first diffraction pattern being associated with a first color of the plurality of color lasers, and the second diffraction pattern being associated with a second color of the plurality of color lasers. In an embodiment, the leveling metrology data includes: (i) substrate height data, and / or (ii) substrate height data converted into displacements in the x and y directions.

[0160] Step P903 includes executing an overlay accuracy prediction model using measurement data 904 related to the current substrate to predict an overlay accuracy error 903 caused by a tool used in a patterning process of the current substrate. In an embodiment, the overlay accuracy prediction model is configured to predict an overlay accuracy error 903 caused by each tool used in the patterning process of the current substrate. In an embodiment, the tool used in the patterning process may be one or more of an etching device, a photolithography device, a chemical mechanical polishing device, or a combination thereof. Figure 2 Therefore, the predicted overlay error 903 includes the overlay error caused by the etching equipment, the photolithography equipment, the chemical mechanical polishing equipment, or a combination thereof.

[0161] In an embodiment, an overlay accuracy prediction model is obtained by: (i) performing a first principal component analysis (PCA) using alignment data associated with a previously patterned substrate or a test substrate, and (ii) performing a second PCA using overlay accuracy error data associated with a previously patterned substrate or a test substrate; and establishing a correlation between components of the first PCA and components of the second PCA.

[0162] In an embodiment, a first PCA of the alignment data produces a first set of principal components that explains the variation in the alignment data, wherein the first set of principal components includes a first set of basis functions and scores associated therewith.

[0163] In an embodiment, a second PCA of the overlay error data produces a second set of principal components that explains variations in the overlay error data, wherein the second set of principal components includes a second set of basis functions and scores associated therewith.

[0164] In an embodiment, one or more principal components of the second set of principal components account for overlay errors caused by a specific process or a specific tool of the patterning process.

[0165] In an embodiment, the correlation between the first principal component and the second principal component converts the alignment data of the current substrate into the predicted overlay error 903 data of the current substrate. In an embodiment, the predicted overlay error 903 data is associated with a specific process to which the current substrate will be subjected.

[0166] Fig.11An exemplary PCA performed using alignment data and overlay accuracy data to further establish an exemplary overlay accuracy prediction model 905 is described. In this example, alignment data and overlay accuracy data can be collected, for example, from 200 training wafers. Using the alignment data of each wafer, an alignment wafer map can be generated for each wafer. Similarly, an overlay accuracy map can be generated for each wafer using the overlay accuracy data. In addition, a principal component analysis (PCA) is performed using the alignment data to generate a first set of principal components that explain the variation of the alignment data of each wafer. Similarly, another PCA is performed using the overlay accuracy data to generate a second set of principal components that explain the variation of the overlay accuracy data of each wafer. In addition, the model is trained to map the principal components of the alignment data and the principal components of the overlay accuracy data. In an embodiment, the PCA space is a linear combination of selected basis functions, such as a first set of basis functions for alignment PCA and a second set of basis functions for overlay accuracy PCA.

[0167] In an embodiment, the reason for mapping the principal component space of the alignment data to the principal component space of the overlay precision data is that a point-to-point mapping of the alignment data to the overlay precision data is not possible. For example, there may be only 20 alignment data points on the entire wafer, while there may be more overlay precision data points (e.g., 300 overlay points) for the same wafer. Therefore, it is extremely difficult to directly map, for example, 20 alignment data points to 300 overlay precision data points. Therefore, in this case, different spaces as PC spaces are used to map or associate between different sets of data.

[0168] In an embodiment, "m" is the number of principal components that can be selected to explain, for example, 95% of the variation in the alignment data. For example, 95% of the variation is explained by 10 principal components (PCs), where each PC has a score associated with it. In other words, the PCs associated with the 10 highest scores are selected. In an embodiment, such scores for the "m" selected PCs are represented in a matrix, such as Fig.11 As shown on the left side of . In this matrix, each column represents a wafer, and the "m" rows represent the scores of the "m" selected PCs. Therefore, in the example, a 200×10 matrix including the scores (eg, represented by ×) can be formed.

[0169] Similarly, a matrix PC corresponding to the selected overlay accuracy PC can be formed OV For example, the selected overlay accuracy PC may be the overlay accuracy PC that explains the most variation in the overlay accuracy data for a particular wafer. In this example, the matrix PC OV A single row is included with the same columns as used in the alignment PC (left). In an embodiment, the single row indicates the score associated with a single selected basis function for the overlay accuracy PC for each wafer.

[0170] In an embodiment, in the overlay accuracy analysis, when determining these overlay accuracy PC features, in most cases, these features are associated with different processes. Therefore, in an embodiment, depending on the process performed on the substrate, the corresponding overlay features can be selected by selecting appropriate basis functions. For example, there may be an overlay accuracy PC specific to the etching process. Therefore, if a person skilled in the art captures the overlay features associated with the etching process, a correction related to the etching process or the process overlay accuracy caused by etching can be performed.

[0171] In addition, based on the alignment PC and the overlay accuracy PC, the model 905 can be trained to map, for example, 10 alignment PC scores to a single overlay accuracy PC score. In an embodiment, for each OV PCA score, a different model can be obtained, such as a first model for mapping a first alignment PC to a first overlay accuracy PC, and a second model for mapping a second alignment PC to a second overlay accuracy PC. After training, the model 905 can predict the overlay score based on any alignment data input to a specific wafer. In addition, the predicted overlay score can be multiplied with the corresponding overlay accuracy PC basis function to obtain the overlay accuracy value of the specific wafer. Another aspect of model building involves using multiple scanners to build the model. This model can then be shared between different scanners.

[0172] Process P905 includes determining, based on performance data 902 and predicted overlay accuracy error 903, an overlay accuracy correction 905 to be applied to another tool where the current substrate will be processed to compensate for the overlay accuracy error caused by the tool. In an embodiment, the tool may be a processing tool (e.g., an etcher / deposition piece) and the other tool may be a scanner, so the scanner is configured to correct the overlay accuracy error introduced by the etcher. For example, the predicted overlay accuracy error 903 may be caused by an etching device. Therefore, the combined overlay accuracy error includes error overlay 903. In this example, an overlay accuracy correction 905 (e.g., substrate level adjustment) is applied to the scanner to correct the overlay accuracy error, which includes the overlay accuracy error 903 caused by the etching device. In an embodiment, substrate adjustment includes orientation of a substrate stage on which the current substrate is mounted; and / or leveling of the substrate stage.

[0173] In an embodiment, determination of an overlay correction includes: combining performance data 902 and predicted overlay errors 903 associated with a tool; and determining a substrate adjustment that minimizes the combined overlay error at another tool for the current substrate. Fig. 9 As shown in , the predicted overlay accuracy error CWP is combined with the overlay accuracy error from the previous processing batch 1.

[0174] In an embodiment, a system for overlay accuracy correction of a current substrate to be patterned is provided. The system includes: a semiconductor manufacturing device (e.g., Figure 1 and Figure 2 ); measurement tools (e.g. Figure 2 ), the metrology tool is used to capture metrology data related to the current substrate to be patterned; a processor (e.g., 104), the processor is configured to communicate with the metrology tool and / or control the semiconductor manufacturing equipment (e.g., based on the overlay accuracy prediction model). In an embodiment, the semiconductor manufacturing equipment used in the patterning process includes: etching equipment; photolithography equipment; chemical mechanical polishing equipment or a combination thereof. In an embodiment, the overlay accuracy prediction model is configured to predict the overlay accuracy error caused by each tool used in the patterning process performed on the current substrate.

[0175] The processor is configured to: execute an overlay accuracy prediction model using metrology data associated with a current substrate; predict an overlay accuracy error caused by a semiconductor manufacturing device used in a patterning process of the current substrate; and determine an overlay accuracy correction to be applied to another tool at which the current substrate will be processed based on the performance data and the predicted overlay accuracy error to compensate for the overlay accuracy error caused by the tool. In an embodiment, the performance data is an average overlay accuracy error value obtained by averaging overlay accuracy error values ​​associated with previously patterned substrates.

[0176] In an embodiment, the processor is configured to determine an overlay correction by: combining performance data and predicted overlay errors associated with semiconductor manufacturing equipment; and determining a substrate adjustment that minimizes the combined overlay error at another semiconductor manufacturing equipment on the current substrate.

[0177] In an embodiment, the processor is further configured to obtain an overlay accuracy prediction model by: (i) performing a first principal component analysis (PCA) using alignment data associated with a previously patterned substrate or a test substrate, and (ii) performing a second PCA using overlay accuracy error data associated with a previously patterned substrate or a test substrate; and establishing a correlation between components of the first PCA and components of the second PCA.

[0178] In an embodiment, the correlation between the first principal component and the second principal component converts the alignment data of the current substrate into predicted overlay error data of the current substrate, the predicted overlay error data being associated with a specific process to which the current substrate will be subjected.

[0179] In an embodiment, metrology data is obtained from a metrology tool (e.g., a sensor). For example, alignment metrology data includes: (i) alignment sensor data, (ii) a residual map generated via an alignment system model, (iii) a substrate quality map including signals with varying intensities indicating the reliability of the alignment data, and / or (iv) a color difference map obtained by projecting multiple color laser beams onto a substrate, each color laser beam being reflected from an alignment mark on a layer of the current substrate, the reflected beams generating a diffraction pattern, the color difference map being a difference between a first diffraction pattern and a second diffraction pattern, the first diffraction pattern being associated with a first color of the multiple color lasers, and the second diffraction pattern being associated with a second color of the multiple color lasers. Another example of metrology data includes obtaining, for example, a residual map generated from a model of the alignment system, a substrate quality map including signals with varying intensities indicating the reliability of the alignment data, and / or (iv) a color difference map obtained by projecting multiple color laser beams onto a substrate, each color laser beam being reflected from an alignment mark on a layer of the current substrate, the reflected beams generating a diffraction pattern, the color difference map being a difference between a first diffraction pattern and a second diffraction pattern, the first diffraction pattern being associated with a first color of the multiple color lasers, and the second diffraction pattern being associated with a second color of the multiple color lasers. Another example of metrology data includes obtaining, for example, Figure 2 The leveling measurement data obtained by the sensor discussed in the above includes: (i) substrate height data, and / or (ii) substrate height data converted into displacements in the x and y directions.

[0180] In an embodiment, the method described herein (e.g., 900) may be implemented as instructions included in a computer-readable medium (e.g., a memory). For example, a non-transitory computer-readable medium includes instructions that, when executed by one or more processors, result in operations including: obtaining (i) performance data associated with a previously patterned substrate (e.g., 902), and (ii) metrology data associated with a current substrate to be patterned (e.g., 904); executing an overlay prediction model using the metrology data associated with the current substrate to predict an overlay error caused by a tool used in a patterning process of the current substrate (e.g., 903); and determining an overlay correction to be applied to another tool at which the current substrate will be processed based on the performance data and the predicted overlay error to compensate for the overlay error caused by the tool.

[0181] In an embodiment, a non-transitory computer readable medium includes instructions for determining an overlay correction based on combined performance data and a predicted overlay error associated with a tool; and determining a substrate adjustment that minimizes the combined overlay error at another tool on a current substrate.

[0182] In an embodiment, a non-transitory computer-readable medium includes instructions for obtaining an overlay accuracy prediction model by performing: (i) performing a first principal component analysis (PCA) using alignment data associated with a previously patterned substrate or a test substrate, and (ii) performing a second PCA using overlay accuracy error data associated with the previously patterned substrate or the test substrate; and establishing a correlation between components of the first PCA and components of the second PCA.

[0183] In an embodiment, a first PCA of the alignment data produces a first set of principal components that explains the variation in the alignment data, wherein the first set of principal components includes a first set of basis functions and scores associated therewith.

[0184] In an embodiment, a second PCA of the overlay error data produces a second set of principal components that explains variations in the overlay error data, wherein the second set of principal components includes a second set of basis functions and scores associated therewith.

[0185] In an embodiment, the correlation between the first principal component and the second principal component converts the alignment data of the current substrate into predicted overlay error data of the current substrate, the predicted overlay error data being associated with a specific process to which the current substrate will be subjected.

[0186] In an embodiment, a non-transitory computer readable medium includes instructions for obtaining metrology data including alignment metrology data and leveling data associated with a current substrate. In an embodiment, the alignment metrology data includes: (i) alignment sensor data, (ii) a residual map generated via an alignment system model, (iii) a substrate quality map including a signal with varying intensity indicating the reliability of the alignment data, and / or (iv) a color difference map obtained by projecting a plurality of color laser beams onto the substrate, each color laser beam being reflected from an alignment mark on a layer of the current substrate, the reflected beams generating a diffraction pattern, the color difference map being a difference between a first diffraction pattern and a second diffraction pattern, the first diffraction pattern being associated with a first color of the plurality of color lasers, and the second diffraction pattern being associated with a second color of the plurality of color lasers. In an embodiment, the leveling metrology data of the current substrate includes: (i) substrate height data, and / or (ii) substrate height data converted into displacements in the x and y directions.

[0187] In an embodiment, the performance data is an average overlay error value obtained by averaging overlay error values ​​associated with previously patterned substrates.In an embodiment, the overlay prediction model is configured to predict the overlay error caused by each tool used in a patterning process for a current substrate.

[0188] In an embodiment, a computer program product includes a non-transitory computer-readable medium having instructions recorded thereon, the instructions being executed by a computer (e.g., Fig.23 ) when executed, implement any of the steps of method 700 or 800 discussed above.

[0189] In an embodiment, determining the training data may involve simulation of a patterning process that may, for example, predict profiles in the resist and / or etched image, CD, edge placement (e.g., edge placement error), etc. The goal of the simulation is to accurately predict, for example, edge placement of the printed pattern, and / or aerial image intensity slope, and / or CD, etc. These values ​​may be compared to the intended design to, for example, correct the patterning process, identify locations where defects are predicted to occur, etc. The intended design is typically defined as a pre-OPC design layout, which may be provided in a standardized digital file format such as GDSII or OASIS or other file formats.

[0190] As discussed earlier, in an embodiment, a model (e.g., a machine learning model) is trained based on process condition data and substrate level data for each patterned substrate. For example, performance data from an alignment sensor, a leveling sensor, or an overlay determination system / algorithm can be used to train a model to infer the overlay accuracy of a current layer or future layers to be patterned on a substrate.

[0191] In existing methods, the amount of measurement data required to train a machine learning model, for example, can be burdensome to the user and impact the throughput of the process. As a result, the user may not measure enough patterned substrates to accurately train the model. Measuring large amounts of data to train or update the model can be considered too expensive to be used in semiconductor manufacturing.

[0192] The present disclosure proposes training a model based on region (e.g., field) specific data of a patterned substrate. In addition, the training model can be updated in a similar manner using newly available performance data of one or more portions of the patterned substrate. In an embodiment, a sample of substrate level performance data is divided into multiple fields. For example, in a batch of 25 substrates, each substrate can be divided into 110 fields, which will produce 2750 samples for training the model. In an embodiment, the performance data used for training can come from alignment, leveling, overlay or other performance-related parameters or indicators. In an embodiment, the performance data can belong to the same layer as the target layer (e.g., top layer) and / or one or more bottom layers below the target layer. The performance data (e.g., overlay accuracy) discussed in the present disclosure is presented by way of example to explain the concepts and does not limit the scope of the present disclosure.

[0193] Fig.12Exemplary performance data for training model 1200 is illustrated. Patterned substrate 1210 is divided into a plurality of portions, for example 110 portions P1 to P110. Multiple portions (e.g., P1 to P110) on all of the plurality of patterned substrates (e.g., 25 substrates) can be stacked on top of each other. In an example, performance data from 25 patterned substrates (each having 110 portions) gives 2750 stacked portions that can be used as a set of training data. In an embodiment, performance data associated with one or more layers BLS is correlated via model 1200 with performance data associated with a target layer TLS (e.g., a top layer).

[0194] Fig.13 1 is a graphical representation of exemplary overlay accuracy data 1300. The overlay accuracy data 1300 may be divided into, for example, fringe fields on a substrate (e.g., Fig.12 Partial fields P1 to P4, P5, P6, P11, P12, etc.) and entire fields (e.g. Fig.12 The overlay accuracy data for each field can be further used to train a model (e.g., model 1200). The trained model can then predict the performance data for each field for any given input performance data.

[0195] In an embodiment, partitioning the performance data into one or more portions (e.g., P1 to P110) of a patterned substrate provides several advantages. For example, only a few patterned substrates or portions of patterned substrates may be measured. Thus, the amount of measurement time may be reduced, making the training / updating of the model cost-effective. Furthermore, even with the reduced measurements, a sufficient amount of data may be available for training the model.

[0196] In an embodiment, the model is trained or updated using available performance data related to the patterned layer, such as overlay (OVL) data. Fig.12 )) to obtain OVL data. The model receives as input OVL data for each field associated with one or more previous layers. In addition, other performance data, such as alignment, leveling, and background data or other data as discussed in the present disclosure, can be used to train the model. In an embodiment, the trained model predicts performance data of future layers to be patterned on the substrate, such as OVL for each field. The predicted OVL for each field is fed forward (FF) to the lithographic equipment to optimize, for example, the exposure of the future layer for each field. An exemplary algorithm that uses the data of the predicted OVL for each field to configure a program or device (e.g., a lithographic equipment) associated with patterning is described in Fig.14 This is explained in the.

[0197] Fig.141 is a block diagram illustrating a feed forward (FF) process for controlling a lithographic apparatus. The feed forward process integrates the predicted performance data of each field of the present disclosure with an advanced process control (APC) process to determine more accurate adjustments to the lithographic apparatus. The APC determines corrections based on, for example, metrology data of a patterned substrate. An exemplary APC is discussed in U.S. Pat. No. 9,177,219 B2, which is incorporated herein by reference in its entirety.

[0198] In this example, Fig.14 14, performance data 1410 associated with patterned substrate layers L11, L12, L13, and L14 of a first batch is obtained, for example, via a metrology tool or sensor. The performance data 1410 may be obtained from patterned substrate layers of a previous batch of substrates (e.g., L1) or a current batch of substrates (e.g., L2). In addition, other performance data 1420 may be obtained from the current substrate being patterned. The current substrate (e.g., 1420) may have patterned layers L22, L23, and L24, and layer L21 is a future layer that is expected to be patterned on the current substrate. In this example, performance data 1420 of a second batch (e.g., L2) of patterned substrates may be used for verification purposes. In this example, performance data 1420 associated with layers L22, L23, and L24 may be obtained (e.g., via a sensor or metrology tool), and performance data associated with future layers (e.g., top layer L21 may be a future layer) may be predicted by training model 1200. In an embodiment, the performance data 1410 includes, for example, the overlay accuracy determined between the first layer L11 and one or more other layers such as layers L12, L13, and L14. Similarly, the performance data 1420 includes, for example, the overlay determined between layers L22 and L23 and layers L22 and L24, and the training model 1200 can be used to predict the overlay accuracy data of the future layer L21.

[0199] In an embodiment, the performance data (e.g., OVL) of layer L21 may be determined as follows. At block 1414, the model 1200 is trained based on the performance data 1410. For example, the model 1200 is trained based on the overlay between layer L12 and layers L13 / L14, and the target overlay between layer L11 and L13 / L14. In addition, the training model 1200 may be executed to determine the performance data of future layers of a subsequent batch (e.g., L2). For example, the training model 1200 predicts the overlay accuracy between the first layer L21 and other layers L22, L23, and L24.

[0200] At block 1412, residual performance data may be calculated as, for example, the difference between the OVL of layer L11 relative to other layers, such as L22 and L23, respectively, and the model predicted OVL at block 1414. In an embodiment, the performance data may be, for example, CD, EPE, OVL in a specific direction, such as x and y, used during double patterning. Additionally, at block 1416, average performance data of block 1412 may be determined for a previous batch of substrates. In an embodiment, data 1410 and 1420 are uncorrected performance data. In an embodiment, at block 1416, average performance data may be obtained from an APC process that models, for example, substrate level performance data (e.g., overlay accuracy) based on metrology data (e.g., 1410) of a patterned substrate.

[0201] At block 1422 , the training model 1200 (at block 1414 ) uses the data 1420 to determine correlations between the first layer L21 and other layers L22 , L23 , and L24 to which the data of block 1416 is added (eg, other layers L22 , L23 , and L24 are examples of layers for future batches).

[0202] As mentioned earlier, the training model 1200 can be applied to the performance data 1420 of the current substrate being patterned to determine the performance data 1422 for each field of each future layer L21 to be formed on the substrate. For example, the performance data of L22, L23, and L24 can be used together with the correlation determined by the training model 1200 to predict the performance data 1422 of the future layer L21. For example, the predicted performance data of the future layer L21 is the data for each field. The predicted data 1422 of L21 can be combined with the average data of the previous substrate (at box 1416) to determine how the patterning process should be configured so that the performance data of the layer L21 is within a specified performance range when patterned. Therefore, forward correction can be applied to the patterning device or process. The patterning process can be adjusted to apply forward correction based on the predicted performance data of L21 and the previously uncorrected performance data. For example, the predicted performance data can be used to adjust the dose, focus, or other parameters of the scanner during the imaging of the layer L21 on the current substrate. In an embodiment, the predicted overlay accuracy data can be used to adjust the alignment and leveling of the substrate. In an embodiment, the predicted EPE or CD data can be used to adjust the dose and focus of the scanner. The adjusted parameters will form a layer L21 with performance (e.g., overlay accuracy, EPE, CD, etc.) within a specified performance threshold, for example.

[0203] Fig.15is a flow chart of a method for training a model for predicting performance data for one or more portions of a substrate. In an embodiment, the method 1500 may be implemented as steps P1501 , P1503 , and P1505 described in further detail below.

[0204] Step P1501 includes obtaining performance data 1501 associated with portions of a plurality of patterned substrate layers formed one on top of another. Examples of performance data 1501 for each portion of the patterned substrate layer are shown in Fig.12 and Fig.13 In an embodiment, obtaining performance data 1501 includes obtaining performance data according to the substrate (see Fig.12 ) to segment the performance data 1501. In an embodiment, a portion of the plurality of portions of the patterned substrate layer is a field, sub-field, or die region of the substrate.

[0205] In an embodiment, the first performance data 1501 and the predicted performance data 1503 include at least one of the following: overlay accuracy data associated with a given layer of the substrate; alignment data associated with a given layer of the substrate; leveling data associated with a given layer of the substrate; correctable overlay accuracy error data associated with a given layer of the substrate (e.g., correctable via alignment, leveling, etc.); height data of a given layer relative to one or more underlying layers on the substrate; or other data measured by a sensor, tool, or measurement system discussed in the present disclosure. For example, alignment data may include orientation or translation of one or more portions of the substrate during patterning. Alignment data may be captured, for example, by an alignment system, and height and / or leveling data may be obtained by a horizontal sensor in a lithographic apparatus, as discussed herein. Similarly, other performance data such as leveling and correctable overlay accuracy error may be obtained via a horizontal sensor and an overlay accuracy measurement system, respectively.

[0206] Process P1503 includes providing performance data 1501 of a portion of a patterned substrate layer as input to a base prediction model to obtain predicted performance data 1503 associated with a portion of a first layer of the substrate. In an embodiment, the model is at least one of the following: a linear model; or a machine learning model. In an embodiment, the machine learning model may be a neural network. For example, the machine learning model may be at least one of the following: a multilayer perceptron; a random forest; an adaptive boosting tree; a support vector regression; a Gaussian process regression; a k-nearest neighbor algorithm; a feedforward; a reproducible neural network; a long / short term memory; a gated reproducible; an autoencoder; a Markov chain; a Hopfield network; a Boltzmann machine; a deep belief network or other version of a neural network. In an embodiment, the machine learning model is an advanced machine learning model including at least one of the following: a residual neural network (RNN); a convolutional neural network (CNN); or a deep CNN. In an embodiment, the RNN model is formulated to include inputs associated with a patterned substrate layer of a current batch of substrates or a patterned substrate layer of a previous batch of substrates as a time axis. RNN has the ability to model correlations between features in the time domain and the frequency domain. This is a way of stacking inputs. For example, in an RNN, a set of filters is convolved with the input, which produces multiple output maps, one for each filter. This is followed by applying an element-wise product-like function, such as the σ(·) function. These operations are performed on input data with two axes, such as a spectrogram (time × frequency).

[0207] Step P1505 includes using the input performance data 1501 associated with the first layer as feedback to update one or more configurations of the base prediction model 1509, wherein the one or more configurations are updated based on a comparison between the input performance data 1501 of the first layer and the predicted performance data 1503. In an embodiment, the performance data 1501 includes data 1501 for prediction and data that may be related to the patterned layer (e.g., after patterning) for updating the model. Fig.14 Data 1501' of actual measurement data associated with layer L21).

[0208] After training, the prediction model 1510 is configured / updated to correlate the performance data 1501 of the first layer with one or more other patterned substrate layers. For example, the training prediction model 1510 can provide relationships between different layers. For example, the relationship between the performance data of the first layer and the second layer, the relationship between the performance data of the first layer and the third layer, the relationship between the performance data of the first layer and the fourth layer, etc. After training the basic model 1509, the model is referred to as a training model or a training prediction model 1510.

[0209] In an embodiment, process P1505 illustrates a method for training a base model 1509 to obtain a trained prediction model 1510. The training of the model 1509 is an iterative process. Each iteration includes: predicting the performance data 1503 associated with the portion of the first layer using the performance data 1501 associated with the portion of the substrate and a given model parameter value (e.g., an initial value set by a user) via the base prediction model 1509; comparing the model-predicted performance data 1503 associated with the portion of the first layer with the obtained performance data 1501 associated with the portion of the first layer; and adjusting the given model parameter value of the base model 1509 based on the difference so that the difference between the model-predicted performance data 1503 associated with the portion of the first layer of the plurality of patterned substrate layers and the obtained performance data 1501 is within a specified range. In an embodiment, the adjustment of the given model parameter value of the base model 1509 is performed until the difference is minimized.

[0210] Fig.16 16 is a flow chart of a method 1600 for controlling a patterning process or patterning equipment based on a feedforward estimate of performance data of a patterned substrate. Using method 1600, the performance of a future layer of a substrate can be improved, which in turn improves the yield of the patterning process. For example, the overlay accuracy of the future layer can be improved by correcting the estimated overlay accuracy using the input of the alignment system. For example, the substrate stage adjustment system can adjust the substrate orientation, translation, or height during the patterning process. In another example, the performance data can be a CD or EPE associated with a feature to be imaged on the top layer. In this example, the dose and / or focus of the scanner can be adjusted based on the estimated performance (e.g., CD, EPE) of the future layer to be formed on the substrate. The feedforward method 1600 for controlling or configuring the patterning process is further discussed in detail in the following steps P1601, P1603, and P1605.

[0211] Step P1601 includes obtaining first performance data 1601 associated with a portion of a plurality of patterned substrate layers of a substrate. In an embodiment, the first performance data 1601 includes substrate-level performance data associated with a current batch of patterned substrates. In an embodiment, the first performance data 1601 also includes substrate-level performance data associated with a previous batch of patterned substrates. In an embodiment, the first performance data 1601 includes performance data associated with a first layer (e.g., a top layer) of the substrate whose performance is to be inferred; and performance data associated with a second layer (e.g., a bottom layer) of the substrate. The second layer is located below the first layer of the substrate. For example, see Fig.14, performance data 1410 associated with layers L11 to L14 or performance data 1420 associated with layers L21 to L24, wherein L21 may be performance data to be predicted. In an embodiment, the portion of the patterned substrate layer is aligned. For example, see also Fig.12 Portions P1 to P110 of the patterned substrate.

[0212] In an embodiment, the first performance data 1601 includes specific performance data divided into parts (see Fig.12 ). In an embodiment, the first performance data 1601 (and predicted performance data 1603) include at least one of the following: overlay accuracy data associated with a given layer of the substrate; alignment data associated with a given layer of the substrate; leveling data associated with a given layer of the substrate; correctable overlay accuracy error data associated with a given layer of the substrate; height data of the given layer relative to one or more underlying layers on the substrate; or other performance-related data as discussed in the present disclosure.

[0213] Step P1603 includes generating predicted performance data 1603 related to one or more portions of a future layer to be formed on the substrate using the first performance data 1601 as input via the training model 1510. In an embodiment, the portion of the substrate is a field, a subfield, or a die region of the substrate. For example, the training model 1510 can be used to predict performance data for one or more portions of a future layer, such as layer L21 of the performance data 1420, as shown in FIG. Fig.14 as shown in .

[0214] Return to reference Fig.16 In an embodiment, the training model 1510 is configured to correlate the first performance data 1601 associated with the first layer with one or more other patterned substrate layers. In an embodiment, the training model 1510 is at least one of the following: a linear model; or a machine learning model. In an embodiment, the machine learning model is at least one of the following: a multilayer perceptron; a random forest; an adaptive boosting tree; a support vector regression; a Gaussian process regression; or a k-nearest neighbor algorithm. In an embodiment, the machine learning model is an advanced machine learning model that includes at least one of the following: a residual neural network (RNN); or a convolutional neural network (CNN). In an embodiment, the RNN model is formulated to include data associated with the patterned substrate layer as a time axis.

[0215] Process P1605 includes generating values ​​1610 for controlling one or more parameters of the patterning process based on first performance data 1601 associated with the patterned substrate layer and predicted performance data 1603 associated with the future layer, so that second performance data associated with the future layer of the substrate is within a specified performance range.

[0216] In an embodiment, generating values ​​1610 of one or more parameters includes: determining uncorrected performance data associated with a patterned substrate layer based on first performance data 1601; determining substrate-level performance data of the future layer based on predicted performance data 1603 related to one or more portions of the future layer; and adjusting values ​​1610 of one or more parameters of the patterning process based on the substrate-level performance data of the future layer and the uncorrected performance data of the patterned substrate layer so that the performance data of the future layer of the substrate is within a specified performance range after patterning.

[0217] In an embodiment, one or more parameters include: dose, focus, alignment of the substrate relative to a reference, height of the substrate, layer thickness, deposition process parameters, and / or etching process parameters. For example, when patterning a future layer, the predicted overlay accuracy of the future layer is applied as an intentional overlay accuracy deviation. For example, the overlay deviation can be implemented and adjusted by the orientation of the substrate relative to a desired reference position or target position on the substrate, the translation of the substrate, the height of the substrate, or a combination thereof. In an embodiment, the estimated overlay accuracy of each substrate portion is calculated in method 1600. Correction can be applied to each portion of the substrate. Therefore, overlay accuracy correction can be performed for each die or field.

[0218] In an embodiment, one or more non-transitory computer-readable media are provided, storing a prediction model and instructions that, when executed by one or more processors, provide the prediction model. In an embodiment, the instructions are similar to method 1600. Fig.23 Examples of one or more non-transitory media are discussed.

[0219] In an embodiment, one or more non-transitory computer-readable media include instructions for generating a predictive model by: obtaining performance data associated with portions of a plurality of patterned substrate layers formed one on top of another; providing the performance data of the portions of the patterned substrate layers as input to a base predictive model to obtain predicted performance data associated with portions of a first layer of the substrate; and using the input performance data associated with the first layer as feedback to update one or more configurations of the base predictive model, wherein the one or more configurations are updated based on a comparison between the input performance data of the first layer and the predicted performance data. The predictive model is structured to correlate the performance data of the first layer with one or more other patterned substrate layers.

[0220] In an embodiment, the instructions for obtaining the performance data include segmenting the performance data according to one or more portions of the substrate.

[0221] In an embodiment, the first performance data and the predicted performance data include at least one of the following: overlay accuracy data associated with a given layer of the substrate; alignment data associated with a given layer of the substrate; leveling data associated with a given layer of the substrate; correctable overlay accuracy error data associated with a given layer of the substrate; or height data of a given layer relative to one or more underlying layers on the substrate.

[0222] In an embodiment, the training of the model is an iterative process. Each iteration includes: predicting the performance data associated with the portion of the first layer using the performance data associated with the portion and a given model parameter value via a base prediction model; comparing the model-predicted performance data associated with the portion of the first layer with the obtained performance data associated with the portion of the first layer; adjusting the given model parameter value of the base model based on the difference so that the difference between the model-predicted performance data associated with the portion of the first layer of the plurality of patterned substrate layers and the obtained performance data is within a specified range.

[0223] In an embodiment, the adjustment of a given model parameter value of the model is performed until the difference is minimized.

[0224] In an embodiment, the model is at least one of the following: a linear model; or a machine learning model. In an embodiment, the machine learning model is at least one of the following: a multilayer perceptron; a random forest; an adaptive boosting tree; a support vector regression; a Gaussian process regression; or a k-nearest neighbor algorithm. In an embodiment, the machine learning model is an advanced machine learning model including at least one of the following: a residual neural network (RNN); or a convolutional neural network (CNN). In an embodiment, the RNN model is formulated to include a patterned substrate layer of a current batch of substrates or a patterned substrate layer of a previous batch of substrates as a time axis.

[0225] In an embodiment, the portions of the patterned substrate layer are fields, sub-fields or die regions of the substrate.

[0226] In an embodiment, the one or more parameters include: a dose of a scanner, a focus of a scanner, an alignment of the substrate relative to a reference, a height of the substrate, a layer thickness, a deposition process parameter, and / or an etching process parameter.

[0227] In an embodiment, a non-transitory computer-readable medium is provided, having instructions thereon, which when executed by a computer, cause the computer to generate a prediction model. The instructions are similar to the steps of method 1500. For example, the instructions include: obtaining first performance data associated with portions of a plurality of patterned substrate layers of a substrate; using the first performance data via a training model to generate predicted performance data associated with one or more portions of a future layer to be formed on the substrate; and based on the first performance data associated with the patterned substrate layer and the predicted performance data associated with the future layer, generating values ​​of one or more parameters for controlling a patterning process so that second performance data associated with the future layer of the substrate is within a specified performance range.

[0228] In an embodiment, the first performance data comprises substrate level performance data associated with a current batch of patterned substrates. In an embodiment, the first performance data further comprises substrate level performance data associated with a previous batch of patterned substrates. In an embodiment, the first performance data comprises performance data associated with a first layer of a substrate; and another performance data associated with a second layer of the substrate, the second layer being located below the first layer of the substrate.

[0229] In an embodiment, the training model is configured to correlate the first performance data associated with the first layer with one or more other patterned substrate layers. Fig.12 and Fig.14 As discussed earlier, in an embodiment, the training model is at least one of the following: a linear model; or a machine learning model. In an embodiment, the machine learning model is at least one of the following: a multilayer perceptron; a random forest; an adaptive boosting tree; a support vector regression; a Gaussian process regression; or a k-nearest neighbor algorithm. In an embodiment, the machine learning model is an advanced machine learning model that includes at least one of the following: a residual neural network (RNN); or a convolutional neural network (CNN). In an embodiment, the RNN model is formulated to include data related to the patterned substrate layer as a time axis.

[0230] In an embodiment, the first performance data and the predicted performance data include at least one of the following: overlay accuracy data associated with a given layer of the substrate; alignment data associated with a given layer of the substrate; leveling data associated with a given layer of the substrate; correctable overlay accuracy error data associated with a given layer of the substrate; or height data of a given layer relative to one or more underlying layers on the substrate.

[0231] In an embodiment, the portion of the patterned substrate layer is aligned.In an embodiment, the portion of the substrate is a field, a sub-field or a die area of ​​the substrate.In an embodiment, the first performance data comprising substrate level performance data is divided into performance data specific to the portion.

[0232] In an embodiment, instructions for generating values ​​of one or more parameters include: determining uncorrected performance data associated with a patterned substrate layer based on first performance data; determining substrate-level performance data of the future layer based on predicted performance data related to one or more portions of the future layer; and adjusting the values ​​of one or more parameters of the patterning process based on the substrate-level performance data of the future layer and the uncorrected performance data of the patterned substrate layer so that the performance data of the future layer of the substrate is within a specified performance range after patterning.

[0233] In an embodiment, the one or more parameters include: dose, focus, alignment of the substrate relative to a reference, height of the substrate, layer thickness, deposition process parameters, and / or etching process parameters.

[0234] In some embodiments, the inspection device may be a scanning electron microscope (SEM) that produces images of structures exposed or transferred on a substrate (eg, some or all structures of a device). Fig.17 An embodiment of a SEM tool is depicted.A primary electron beam EBP emitted from an electron source ESO is converged by a converging lens CL and then passes through a beam deflector EBD1 , an E×B deflector EBD2 and an objective lens OL to illuminate a substrate PSub on a substrate stage ST at a focal point.

[0235] When the substrate PSub is irradiated by the electron beam EBP, secondary electrons are generated by the substrate PSub. The secondary electrons are deflected by the E×B deflector EBD2 and detected by the secondary electron detector SED. A two-dimensional electron beam image can be obtained by detecting the electrons generated from the sample in synchronization with, for example, two-dimensional scanning of the electron beam by the beam deflector EBD1 in the X or Y direction or repeated scanning of the electron beam EBP by the beam deflector EBD1, and continuously moving the substrate PSub in the other of the X or Y directions by the substrate stage ST.

[0236] The signal detected by the secondary electron detector SED is converted into a digital signal by an analog / digital (A / D) converter ADC, and the digital signal is sent to the image processing system IPS. In an embodiment, the image processing system IPS may have a memory MEM to store all or part of the digital image for processing by the processing unit PU. The processing unit PU (for example, specially designed hardware or a combination of hardware and software) is configured to convert or process the digital image into a set of data representing the digital image. In addition, the image processing system IPS may have a storage medium STOR configured to store a set of digital images and corresponding data in a reference database. The display device DIS can be connected to the image processing system IPS so that the operator can perform necessary operations of the device with the help of a graphical user interface.

[0237] As mentioned above, SEM images can be processed to extract contours describing the edges of objects representing device structures in the image. These contours are then quantified via metrics such as CD. Therefore, images of device structures are often compared and quantified via oversimplified metrics such as distance between edges (CD) or simple pixel differences between images. Typical contour models for detecting the edges of objects in images in order to measure CD use image gradients. In practice, those models rely on strong image gradients. However, in reality, images are often noisy and have discontinuous boundaries. Techniques such as smoothing, adaptive thresholding, edge detection, abrasion, and dilation can be used to process the results of image gradient contour models to address noisy and discontinuous images, but will ultimately result in low-resolution quantification of high-resolution images. Therefore, in most cases, mathematical manipulation of images of device structures to reduce noise and automate edge detection results in a loss of resolution of the image, thereby resulting in a loss of information. Therefore, the result is a low-resolution quantification equivalent to an oversimplified representation of a complex high-resolution structure.

[0238] Therefore, it is desirable to have a mathematical representation that preserves resolution and yet describes the general shape of a structure (e.g., a circuit feature, an alignment mark, or a portion of a metrology target (e.g., a grating feature), etc.) produced or expected to be produced using a patterning process, whether, for example, the structure is in a latent resist image, in a developed resist image, or a layer transferred to a substrate, such as by etching. In the context of lithography or other patterning processes, the structure can be a fabricated device or a portion of a fabricated device, and the image can be a SEM image of the structure. In some cases, the structure can be a feature of a semiconductor device, such as an integrated circuit. In this case, the structure can be referred to as a pattern or a desired pattern including multiple features of a semiconductor device. In some cases, the structure can be an alignment mark or a portion of the alignment mark (e.g., a grating of an alignment mark) used in an alignment measurement process to determine the alignment of one object (e.g., a substrate) with another object (e.g., a patterning device), or a metrology target or a portion of the metrology target (e.g., a grating of a metrology target) used to measure parameters of a patterning process (e.g., overlay, focus, dose, etc.). In an embodiment, the metrology target is a diffraction grating used to measure, for example, overlay accuracy.

[0239] Fig.18 Another embodiment of the inspection device is schematically illustrated. The system is used to inspect a sample 90 (such as a substrate) on a sample platform 89 and includes a charged particle beam generator 81, a converging lens module 82, a probe forming objective lens module 83, a charged particle beam deflection module 84, a secondary charged particle detector module 85, and an image forming module 86.

[0240] The charged particle beam generator 81 generates a primary charged particle beam 91. The converging lens module 82 converges the generated primary charged particle beam 91. The probe forming objective lens module 83 focuses the converged primary charged particle beam into a charged particle beam probe 92. The charged particle beam deflection module 84 causes the formed charged particle beam probe 92 to scan the surface of the entire region of interest on the sample 90 fastened on the sample platform 89. In an embodiment, the charged particle beam generator 81, the converging lens module 82 and the probe forming objective lens module 83 or their equivalent designs, alternatives or any combination thereof together form a charged particle beam probe generator that generates a scanning charged particle beam probe 92.

[0241] The secondary charged particle detector module 85 detects secondary charged particles 93 emitted from the sample surface when bombarded by the charged particle beam probe 92 (also together with other reflected or scattered charged particles from the sample surface) to generate a secondary charged particle detection signal 94. An image forming module 86 (e.g., a computing device) is connected to the secondary charged particle detector module 85 to receive the secondary charged particle detection signal 94 from the secondary charged particle detector module 85 and form at least one scanning image accordingly. In an embodiment, the secondary charged particle detector module 85 and the image forming module 86 or their equivalent designs, alternatives or any combination thereof together form an image forming device that forms a scanning image from the detected secondary charged particles emitted from the sample 90 bombarded by the charged particle beam probe 92.

[0242] In an embodiment, the monitoring module 87 is coupled to the image forming module 86 of the image forming device to monitor, control, etc. the patterning process and / or use the scanned image of the sample 90 received from the image forming module 86 to derive parameters for patterning process design, control, monitoring, etc. Thus, in an embodiment, the monitoring module 87 is configured or programmed to perform the methods described herein. In an embodiment, the monitoring module 87 includes a computing device. In an embodiment, the monitoring module 87 includes a computer program for providing the functionality herein and encoded on a computer readable medium formed or disposed within the monitoring module 87.

[0243] In an embodiment, similar to using a probe to detect the substrate Fig.17 Electron beam inspection tools, Fig.18 The electron current in a system such as Fig.17 The CD SEM depicted in is significantly larger, so that the probe spot is large enough so that the detection speed can be fast. However, due to the large probe spot, the resolution may not be as high as that of the CD SEM. In embodiments, without limiting the scope of the present disclosure, the inspection apparatus discussed above may be a single beam device or a multi-beam device.

[0244] Can process from e.g. Fig.17 and / or Fig.18 The SEM images of the system are taken to extract the contours in the image that represent the edges of the object, which represent the device structure. These contours are then quantified via a metric such as CD, usually at a user-defined tangent line. Thus, the images of the device structure are usually compared and quantified via a metric such as the distance between the edges (CD) measured for the extracted contours or a simple pixel difference between the images.

[0245] Fig.19An exemplary inspection device (e.g., a scatterometer) is depicted. The inspection device comprises a broadband (white light) radiation projector 2 that projects radiation onto a substrate W. The redirected radiation is passed to a spectrometer detector 4, which measures a spectrum 10 of the specularly reflected radiation (with an intensity that varies as a function of wavelength), such as shown in the lower left graph. From this data, the processor PU can analyze the specularly reflected radiation, such as by rigorous coupled wave analysis and nonlinear regression or by comparing the specularly reflected radiation to the substrate W. Fig.19 The structure or profile that resulted in the detected spectrum is reconstructed by comparing the simulated spectrum library shown in the lower right of FIG. Typically, for the reconstruction, the general form of the structure is known, and some variables are assumed based on knowledge of the process used to make the structure, leaving only a few variables of the structure to be determined from the measurement data. This inspection device can be configured as a normal incidence inspection device or an oblique incidence inspection device.

[0246] Fig.15 Another inspection apparatus that can be used is shown in . In this arrangement, radiation emitted by a radiation source 2 is collimated using a lens system 12 and transmitted through an interference filter 13 and a polarizer 17, reflected by a partially reflective surface 16 and focused into a spot S on a substrate W via an objective lens 15, which has a high numerical aperture (NA), ideally at least 0.9 or at least 0.95. Immersion inspection apparatus (using a relatively high refractive index fluid, such as water) can even have a numerical aperture greater than 1.

[0247] As in the lithographic apparatus LA, one or more substrate tables may be provided to hold a substrate W during measurement operations. The substrate table may be similar in form to Figure 1The substrate table WT of the inspection apparatus is similar or identical to that of the lithographic apparatus. In an example in which the inspection apparatus is formed integrally with the lithographic apparatus, the substrate table may even be the same substrate table. A coarse positioner and a fine positioner may be provided to a second positioner PW, which is configured to accurately position the substrate relative to the measuring optical system. A plurality of sensors and actuators are provided, for example, to acquire the position of an object of interest and to bring the object of interest into position below the objective lens 15. Typically, many measurements will be made of the object at different locations across the substrate W. The substrate support may be moved in the X and Y directions to acquire different targets, and the substrate support may be moved in the Z direction to acquire the desired location of the target relative to the focus of the optical system. For example, when in fact the optical system can remain substantially stationary (typically in the X and Y directions, but possibly also in the Z direction) and only the substrate moves, it is convenient to consider and describe the operation as if the objective lens is brought into different locations relative to the substrate. Provided that the relative position of substrate and optical system is correct, it does not matter in principle which of the substrate and the optical system moves in the real world, or whether both move, or whether a combination of a part of the optical system is moving (e.g. in the Z direction and / or in a tilt direction), wherein the rest of the optical system is stationary and the substrate is moving (e.g. in the X and Y directions and optionally also in the Z direction and / or in a tilt direction).

[0248] The radiation redirected by the substrate W is then passed through the partially reflective surface 16 to the detector 18 so that the spectrum can be detected. The detector 18 can be located at the back-projection focal plane 11 (i.e., at the focal length of the lens system 15), or the plane 11 can be re-imaged onto the detector 18 using auxiliary optical devices (not shown in the figure). The detector can be a two-dimensional detector so that a two-dimensional angular scatter spectrum of the substrate target 30 can be measured. The detector 18 can be, for example, an array of CCD or CMOS sensors, and an integration time of, for example, 40 milliseconds per frame can be used.

[0249] The reference beam can be used, for example, to measure the intensity of the incident radiation. To perform this measurement, when the radiation beam is incident on the partially reflecting surface 16, part of the radiation beam is transmitted through the partially reflecting surface 16 towards the reference mirror 14 as a reference beam. The reference beam is then projected onto a different part of the same detector 18 or alternatively onto a different detector (not shown in the figure).

[0250] One or more interference filters 13 may be used to select wavelengths of interest in the range of, for example, 405 nm to 790 nm or even lower, such as 200 nm to 300 nm. The interference filter may be tunable, rather than comprising a collection of different filters. A grating may be used in place of the interference filter. An aperture stop or spatial light modulator (not shown) may be provided in the illumination path to control the range of angles of incidence of the radiation on the target.

[0251] The detector 18 can measure the intensity of the redirected radiation at a single wavelength (or a narrow wavelength range), the intensity of the redirected radiation at multiple wavelengths separately, or the intensity of the redirected radiation integrated over the entire wavelength range. In addition, the detector can separately measure the intensity of the transverse magnetic polarized radiation and the transverse electric polarized radiation, and / or the phase difference between the transverse magnetic polarized radiation and the transverse electric polarized radiation.

[0252] The target 30 on the substrate W may be a one-dimensional grating that is printed so that after development, the strips are formed by solid resist lines. The target 30 may be a two-dimensional grating that is printed so that after development, the grating is formed by solid resist columns or through holes in the resist. The strips, columns or through holes may be etched into or onto the substrate (e.g., etched into one or more layers on the substrate). The pattern (e.g., of the strips, columns or through holes) is sensitive to changes in processing in the patterning process (e.g., optical aberrations, focus changes, dose changes, etc. in the lithographic projection equipment (particularly the projection system PS)) and will show changes in the printed grating. Therefore, the measurement data of the printed grating is used to reconstruct the grating. One or more parameters of the one-dimensional grating (such as line width and / or shape) or one or more parameters of the two-dimensional grating (such as column or through hole width or length or shape) may be input to a reconstruction program executed by the processor PU based on knowledge of the printing step and / or other inspection processes.

[0253] In addition to the measurement of parameters by reconstruction, angle-resolved scatterometry is also used for the measurement of asymmetry of features in the product and / or resist pattern. A particular application of asymmetry measurement is for the measurement of overlay accuracy, where the target 30 includes a set of periodic features superimposed on another set of periodic features. For example, the use of Fig.19 or Fig.15 The concept of asymmetry measurement by an instrument of the type described herein is incorporated herein in its entirety. Simply stated, while the positions of the diffraction orders in the diffraction spectrum of a target are determined solely by the periodicity of the target, the asymmetry in the diffraction spectrum is indicative of the asymmetry of the individual features that make up the target. Fig.15 In an instrument where the detector 18 may be an image sensor, this asymmetry of the diffraction orders manifests itself directly as an asymmetry of the pupil image recorded by the detector 18. This asymmetry may be measured by digital image processing in the unit PU and calibrated relative to a known overlay accuracy value.

[0254] Fig.21 a plan view illustrating a typical target 30, and Fig.15The range of the illumination spot S in the device. In order to obtain a diffraction spectrum free from interference from surrounding structures, in an embodiment, the target 30 is a periodic structure (e.g., a grating) that is larger than the width (e.g., diameter) of the illumination spot S. The width of the spot S may be smaller than the width and length of the target. In other words, the target is "underfilled" by the illumination, and the diffraction signal is substantially free of any signal from product features and the like outside the target itself. The illumination device 2, 12, 13, 17 may be configured to provide illumination of uniform intensity across the back focal plane of the objective lens 15. Alternatively, the illumination may be limited to an on-axis direction or an off-axis direction, for example by including an aperture in the illumination path.

[0255] Fig. 22 An exemplary process for determining values ​​of one or more variables of interest for a target pattern 30' based on metrology data obtained using metrology is schematically depicted.The radiation detected by the detector 18 provides a measured radiation distribution 108 for the target 30'.

[0256] For a given target 30', a radiation distribution 208 may be calculated / simulated according to a parameterized model 206 using, for example, a numerical Maxwell solver 210. The parameterized model 206 shows exemplary layers of various materials that make up the target and are associated with the target. The parameterized model 206 may include one or more of the variables for the features and layers of the portion of the target under consideration, which one or more of the variables may be varied and derived. Fig. 22 As shown in , the one or more of the variables may include the thickness t of one or more layers, the width w (e.g., CD) of one or more features, the height h of one or more features, and / or the sidewall angle α of one or more features. Although not shown in the figure, the one or more of the variables may also include, but are not limited to: the refractive index of one or more layers in the layer (e.g., real refractive index or complex refractive index, refractive index tensor, etc.), the extinction coefficient of one or more layers, the absorptivity of one or more layers, the resist loss during development, the footing of one or more features, and / or the line edge roughness of one or more features. The initial values ​​of these variables may be the values ​​expected for the target being measured. Then, at 212, the measured radiation distribution 108 is compared with the calculated radiation distribution 208 to determine the difference between the two. If there is a difference, the value of one or more of the variables of the parameterized model 206 can be changed, and a new calculated radiation distribution 208 can be calculated and compared with the measured radiation distribution 108 until there is a sufficient match between the measured radiation distribution 108 and the calculated radiation distribution 208. At this point, the values ​​of the variables of the parameterized model 206 provide a good or optimal match to the geometry of the actual target 30'. In an embodiment, a sufficient match exists when the difference between the measured radiation distribution 108 and the calculated radiation distribution 208 is within a tolerance threshold.

[0257] The variables of the patterning process are referred to as "process variables". The patterning process may include processes upstream and downstream of the actual transfer of the pattern in the lithographic apparatus. The process variables may be grouped into different categories. The first category may be variables of the lithographic apparatus or any other device used in the lithographic process. Examples of this category include variables of the irradiation parts, projection system, substrate platform, etc. of the lithographic apparatus. The second category may be variables of one or more processes performed in the patterning process. Examples of this category include focus control or focus measurement, dose control or dose measurement, bandwidth, exposure duration, development temperature, chemical components used in development, etc. The third category may be variables of the design layout and its implementation in or using the patterning device. Examples of this category may include the shape and / or location of the assist features, adjustments applied by resolution enhancement technology (RET), CD of mask features, etc. The fourth category may be variables of the substrate. Examples include characteristics of the structure below the resist layer, the chemical composition and / or physical size of the resist layer, etc. The fifth category may be characteristics of the time variation of one or more variables of the patterning process. Examples of this category include characteristics of high frequency stage movement (e.g., frequency, amplitude, etc.), high frequency laser bandwidth changes (e.g., frequency, amplitude, etc.), and / or high frequency laser wavelength changes. These high frequency changes or movements are high frequency changes or movements that are higher than the response time of the mechanism used to adjust the basic variables (e.g., stage position, laser intensity). A sixth category may be characteristics of processes upstream or downstream of pattern transfer in a lithographic apparatus, such as spin coating, post-exposure bake (PEB), development, etching, deposition, doping, and / or packaging.

[0258] As will be appreciated, many, if not all, of these variables will have an impact on the parameters of the patterning process and often on the parameters of interest. Non-limiting examples of parameters of the patterning process may include critical dimension (CD), critical dimension uniformity (CDU), focus, overlay, edge position or placement, sidewall angle, pattern shift, etc. Typically, these parameters express errors relative to nominal values ​​(e.g., design values, averages, etc.). Parameter values ​​may be values ​​of characteristics of individual patterns or statistics of characteristics of groups of patterns (e.g., averages, variances, etc.).

[0259] The values ​​of some or all of the process variables or parameters related thereto may be determined by suitable methods. For example, the values ​​may be determined based on data obtained using various metrology tools (e.g., substrate metrology tools). The values ​​may be obtained from various sensors or systems of equipment in the patterning process (e.g., sensors of the lithographic equipment (such as leveling sensors or alignment sensors), control systems of the lithographic equipment (e.g., substrate or patterning device stage control systems), sensors in track tools, etc.). The values ​​may come from an operator of the patterning process.

[0260] Further embodiments of the invention are disclosed in the following list of numbered aspects:

[0261] 1. A method for determining a model for predicting uncorrected overlay accuracy data associated with a current substrate being patterned, the method comprising:

[0262] obtaining (i) a set of first data associated with one or more previous layers and / or a current layer of a current substrate being patterned, (ii) a set of second data comprising overlay accuracy metrology data associated with one or more previous substrates patterned prior to the current substrate, and (iii) uncorrected measured overlay accuracy data associated with a current layer of the current substrate; and

[0263] determining values ​​for a set of model parameters associated with the model based on (i) the first set of data, (ii) the second set of data, and (iii) the metrology data such that the model predicts uncorrected overlay accuracy data for the current substrate,

[0264] The values ​​of the model parameters are determined so as to minimize a cost function, wherein the cost function includes the difference between the predicted data and the measured data.

[0265] 2. The method according to aspect 1, wherein the first data set further includes:

[0266] scanner data associated with one or more scanners used to pattern one or more previous layers of the current substrate and / or the current layer, and

[0267] Manufacturing context data associated with processing tools to which the current substrate has been subjected before the current layer is patterned or to which the current substrate will be subjected after the current layer is patterned.

[0268] 3. The method of claim 2, wherein the scanner data comprises one or more of the following:

[0269] a scanner identifier and a scanner chuck identifier associated with the one or more scanners;

[0270] measurements calculated by sensors or measurement systems of the one or more scanners;

[0271] one or more key performance indicators associated with the one or more scanners and related to overlay accuracy of the current substrate; and

[0272] Measurement data obtained from alignment sensors, leveling sensors, height sensors, or other sensors attached to the one or more scanners.

[0273] 4. The method according to aspect 2, wherein the tools used in the manufacturing include one or more of an etching chamber, a chemical mechanical polishing tool, an overlay accuracy measurement tool, and / or a CD measurement tool.

[0274] 5. The method according to any one of aspects 1 to 4, wherein the set of the first data comprises:

[0275] Overlay accuracy measurement data of one or more previous layers of the current substrate and / or the current layer, the overlay accuracy measurement data comprising: (i) measured overlay accuracy data obtained after applying an overlay accuracy correction to the one or more previous layers of the current substrate, and / or (ii) uncorrected overlay accuracy data obtained before applying the overlay accuracy correction to the one or more previous layers of the current substrate;

[0276] alignment metrology data of one or more previous layers of the current substrate and / or the current layer, the alignment metrology data comprising: (i) alignment sensor data, (ii) a residual map generated by an alignment system model, (iii) a substrate quality map including signals with varying intensities indicating the reliability of the alignment data, and / or (iv) an inter-color difference map obtained by projecting a plurality of color laser beams onto the substrate, each color laser beam being reflected from an alignment mark on the one or more previous layers, the reflected beams generating a diffraction pattern, the inter-color difference map being a difference between a first diffraction pattern and a second diffraction pattern, the first diffraction pattern being associated with a first color of the plurality of color lasers, and the second diffraction pattern being associated with a second color of the plurality of color lasers;

[0277] Leveling metrology data of one or more previous layers and / or the current layer of the current substrate, the leveling metrology data comprising: (i) substrate height data, and / or (ii) the substrate height data converted into displacements in the x and y directions; and / or

[0278] Manufacturing background information of one or more previous layers of the current substrate and / or the current layer, the background information comprising: (i) a lag time associated with a process in the patterning process, (ii) an identifier of a chuck on which the current substrate is mounted, (iii) a chamber identifier indicating a chamber in which the process of the patterning process is performed, and / or (iv) chamber characteristics characterizing an overlay accuracy contribution of one or more processing parameters associated with the chamber.

[0279] 6. The method according to any one of aspects 1 to 5, wherein the first data set further comprises:

[0280] Derived data associated with parameters of the patterning process that contribute to overlay accuracy, wherein the derived data is derived from the scanner data and / or the manufacturing context information.

[0281] 7. The method of any one of clauses 1 to 6, wherein the model is configured to predict uncorrected overlay accuracy data at a point level of the current substrate, wherein a point is a location associated with an overlay mark formed on the current substrate.

[0282] 8. The method of any one of clauses 1 to 7, wherein the model is a point level model, wherein the values ​​of the model parameters of the point level model are determined based on a set of the first data obtained at a given location among a plurality of locations on the current substrate having the overlay mark, a set of the second data, and the uncorrected measured overlay accuracy data.

[0283] 9. The method according to aspect 8, wherein obtaining the set of the first data, the set of the second data, and the set of the uncorrected measured overlay accuracy data at the given location on the current substrate having the overlay mark comprises:

[0284] representing the set of the first data, the set of the second data, and the value of the uncorrected measured overlay accuracy data in the form of corresponding substrate maps;

[0285] aligning each of the substrate maps via modeling and / or interpolation;

[0286] uniformly sharing substrate level information across the current substrate in the first set of data, the second set of data, and the uncorrected measured overlay accuracy data, respectively; and

[0287] The values ​​of the first set of data, the second set of data, and the uncorrected measured overlay accuracy data associated with the given location are extracted respectively.

[0288] 10. The method of clause 9, wherein the substrate level information comprises at least one of: the chuck identifier, or the lag time associated with a processing tool used in a patterning process for the current substrate.

[0289] 11. The method of any one of clauses 1 to 2, wherein the model is configured to predict uncorrected overlay accuracy data at substrate level.

[0290] 12. The method of any one of clauses 1 to 11, wherein the model is a substrate level model, wherein the values ​​of the model parameters of the substrate level model are determined based on the set of the first data, the set of the second data, and the values ​​of the uncorrected measured overlay accuracy data over the entire substrate.

[0291] 13. The method according to claim 12, wherein the step of determining the value of the model parameter of the substrate model further comprises:

[0292] generating a plurality of substrate maps using the set of the first data, the set of the second data, and the value of the uncorrected measured overlay accuracy data respectively associated with each of a plurality of substrates;

[0293] projecting each of the plurality of substrate maps to a basis function; and

[0294] Projection coefficients associated with the basis functions are determined based on the projections, and the projection coefficients and other substrate level data are used to define the substrate model.

[0295] 14. The method of clause 13, wherein projecting the substrate image onto the basis function comprises:

[0296] Perform principal components analysis; or

[0297] A single value decomposition of the substrate graph is performed.

[0298] 15. A method as described in any one of clauses 13 to 14, wherein the basis functions are a set of Zernike polynomials and the projection coefficients are Zernike coefficients, each Zernike coefficient being associated with a corresponding Zernike polynomial of the set of Zernike polynomials.

[0299] 16. The method of any one of clauses 1 to 15, wherein the first set of data, the second set of data and the uncorrected measured overlay accuracy data are pre-processed to extract desired information from the respective sets of data.

[0300] 17. The method according to aspect 16, wherein the desired information is at least one of the following:

[0301] Align system model residual data;

[0302] Levelling the relevant residual data; and / or

[0303] Correctable overlay error data.

[0304] 18. The method of any one of aspects 1 to 17, wherein the model is at least one of the following:

[0305] a linear model determined based on (i) a set of the first data associated with a selected layer of the current substrate or the previous substrate, or (ii) a set of the first data associated with a plurality of layers of the current substrate or the previous substrate; or

[0306] Machine learning models.

[0307] 19. The method of clause 18, wherein the machine learning model is at least one of: a multilayer perceptron; a random forest; an adaptive boosted tree; support vector regression; a Gaussian process regression; or a k-nearest neighbor algorithm.

[0308] 20. The method of clause 18, wherein the machine learning model is an advanced machine learning model, and the advanced machine learning model comprises at least one of a residual neural network (RNN) or a convolutional neural network (CNN).

[0309] 21. The method according to clause 20, wherein the RNN model is formulated to include the current substrate or a previous layer of the previous substrate as a time axis.

[0310] 22. A method according to any one of aspects 1 to 21, wherein the cost function is at least one of the following:

[0311] a first function, wherein the first average error is an nth order error calculated using an absolute difference between predicted data and reference data and raising the difference to the nth order, wherein the predicted data is an overlay accuracy value associated with a given point on a given substrate or a projection coefficient associated with a given substrate and the reference data; or

[0312] a second function (M3S) calculated using the sum of the absolute value of a mean and three times a standard deviation, wherein the mean and the standard deviation are obtained based on a difference between predicted uncorrected overlay accuracy data and the reference data, the predicted data being an overlay accuracy value associated with the given point on the given substrate; or

[0313] The on-product overlay accuracy is calculated using the sum of the mean value of the M3S and 1.96 times the standard deviation of the M3S, wherein the mean value and standard deviation of the M3S are calculated using predicted data as overlay accuracy values ​​associated with a series of given substrates.

[0314] 23. The method of clause 22, wherein determining the point level model comprises:

[0315] executing the point level model using initial model parameter values ​​using data associated with each given location of the plurality of locations on the current substrate to predict the uncorrected overlay accuracy data; and

[0316] Values ​​of the model parameters are determined based on the predicted uncorrected overlay accuracy data at the multiple locations and the measurement data so as to minimize the first function, the second function and / or the on-product overlay accuracy associated with each given location among the multiple locations on the given substrate.

[0317] 24. The method of clause 22, wherein determining the substrate level model comprises:

[0318] using the substrate model to predict the projection coefficients associated with the basis functions;

[0319] constructing an overlay accuracy map based on the predicted projection coefficients;

[0320] Calculating the first function, the second function, or the on-product overlay accuracy based on a difference between the constructed overlay accuracy map and a reference overlay accuracy map; and

[0321] The values ​​of the model parameters are determined so as to minimize the first function, the second function, or the overlay accuracy on the product.

[0322] 25. The method of any one of clauses 1 to 24, wherein the cost function is reduced or minimized using a gradient-based method.

[0323] 26. The method of any one of clauses 1 to 25, wherein the set of first data or the set of second data is an incomplete set of data, wherein overlay metrology data and / or background data associated with one or more of the previous substrates or one or more previous layers of the current substrate are omitted.

[0324] 27. The method of clause 26, wherein the incomplete overlay accuracy data is replaced by average overlay accuracy data, wherein the average overlay accuracy data is calculated based on batches of substrates or based on grouping of the substrates based on the background data.

[0325] 28. The method of clause 26, wherein the incomplete overlay accuracy data is replaced by overlay accuracy data based on domain knowledge, wherein the domain knowledge based overlay accuracy data is generated using computational metrology, wherein the computational metrology includes an overlay accuracy prediction model based on parameters of the patterning process.

[0326] 29. The method of any one of aspects 1 to 28, wherein the model is structured as a two-level hierarchical model.

[0327] 30. The method of clause 29, wherein the first level of the hierarchical model is configured to predict overlay accuracy data using inputs that are always present including data in the first set of data and the second set of data, and

[0328] The second level of the hierarchical model predicts overlay accuracy improvements to the predicted overlay accuracy data of the first level based on inputs that are not always present, including overlay accuracy and certain background data.

[0329] 31. The method according to any one of aspects 1 to 30, further comprising:

[0330] Overlay accuracy correction or control parameters associated with the patterning device are determined based on the predicted uncorrected overlay accuracy data to improve overlay performance of the patterning device.

[0331] 32. A method for updating a trained model for predicting uncorrected overlay accuracy data associated with a current substrate being patterned, the method comprising:

[0332] obtaining (i) a set of first data associated with one or more previous layers of a current substrate being patterned, (ii) a set of second data comprising overlay accuracy metrology data associated with one or more previous substrates patterned prior to the current substrate, and (iii) uncorrected measured overlay accuracy data associated with the current substrate;

[0333] updating the training model based on the first set of data, the second set of data, and the uncorrected measured overlay accuracy data associated with the current substrate such that a cost function associated with the training model is reduced,

[0334] The cost function comprises a difference between predicted uncorrected overlay accuracy data and the uncorrected measured overlay accuracy data, the predicted data being obtained by executing the training model using the set of the first data and the set of the second data.

[0335] 33. The method of clause 32, wherein the cost function is at least one of:

[0336] a first function, wherein the first average error is an nth order error calculated using an absolute difference between predicted data and reference data and raising the difference to the nth order, wherein the predicted data is an overlay accuracy value associated with a given point on a given substrate or a projection coefficient associated with the given substrate and the reference data; or

[0337] a second function (M3S) calculated using the sum of the absolute value of a mean and three times a standard deviation, wherein the mean and the standard deviation are obtained based on a difference between predicted uncorrected overlay accuracy data and the reference data, the predicted data being an overlay accuracy value associated with the given point on the given substrate; or

[0338] The on-product overlay accuracy is calculated using the sum of the mean value of the M3S and 1.96 times the standard deviation of the M3S, wherein the mean value and standard deviation of the M3S are calculated using predicted data as overlay accuracy values ​​associated with a series of given substrates.

[0339] 34. The method of any one of clauses 32 to 33, wherein the set of first data or the set of second data is a set of incomplete data, wherein overlay metrology data and / or background data associated with one or more of the previous substrates or one or more previous layers of the current substrate are omitted.

[0340] 35. The method of clause 34, wherein the incomplete overlay accuracy data is replaced by average overlay accuracy data, wherein the average overlay accuracy data is calculated based on batches of substrates or based on grouping of the substrates based on the background data.

[0341] 36. The method of clause 34, wherein the incomplete overlay accuracy data is replaced by overlay accuracy data based on domain knowledge, wherein the domain knowledge based overlay accuracy data is generated using computational metrology, wherein the computational metrology includes an overlay accuracy prediction model based on parameters of the patterning process.

[0342] 37. A computer program product, comprising a non-transitory computer-readable medium, on which instructions are recorded, and when the instructions are executed by a computer, the steps of the method according to any one of aspects 1 to 36 are implemented.

[0343] 38. A method of determining an overlay accuracy correction for a current substrate to be patterned, the method comprising:

[0344] obtaining (i) performance data associated with a previously patterned substrate, and (ii) metrology data associated with the current substrate to be patterned;

[0345] executing an overlay prediction model using the metrology data associated with the current substrate to predict an overlay error caused by a tool used in a patterning process of the current substrate; and

[0346] Based on the performance data and the predicted overlay error, an overlay correction is determined to be applied to another tool at which the current substrate will be processed to compensate for the overlay error caused by the tool.

[0347] 39. The method of clause 38, wherein the performance data includes overlay error data of the previously patterned substrate.

[0348] 40. The method of clause 39, wherein determining the overlay accuracy correction comprises:

[0349] combining the performance data with a predicted overlay error associated with the tool; and

[0350] A substrate adjustment is determined that minimizes the combined overlay error at the other tool used in a patterning process of the current substrate.

[0351] 41. The method of clause 40, wherein the substrate adjustment comprises:

[0352] the orientation of a substrate table on which the current substrate is mounted; and / or

[0353] Leveling of the substrate table.

[0354] 42. The method according to any one of aspects 38 to 41, wherein the overlay accuracy prediction model is obtained by:

[0355] (i) performing a first principal component analysis (PCA) using alignment data associated with the previous patterned substrate or the test substrate, and (ii) performing a second PCA using overlay error data associated with the previous patterned substrate or the test substrate; and

[0356] A correlation is established between the components of the first PCA and the components of the second PCA.

[0357] 43. The method of clause 42, wherein the first PCA of the alignment data produces a first set of principal components that explain variations in the alignment data, wherein the first set of principal components includes a first set of basis functions and scores associated with the first set of basis functions.

[0358] 44. The method of clause 42, wherein the second PCA of the overlay error data produces a second set of principal components that explain variations in the overlay error data, wherein the second set of principal components includes a second set of basis functions and scores associated with the second set of basis functions.

[0359] 45. The method of clause 44, wherein one or more principal components of the second set of principal components account for overlay errors caused by a specific process or a specific tool of the patterning process.

[0360] 46. ​​The method of clause 42, wherein the correlation between the first principal component and the second principal component converts the alignment data of the current substrate into predicted overlay error data of the current substrate, the predicted overlay error data being associated with a particular process to which the current substrate will be subjected.

[0361] 47. A method according to any one of aspects 38 to 46, wherein the measurement data comprises:

[0362] Alignment metrology data associated with the current substrate, the alignment metrology data comprising: (i) alignment sensor data, (ii) a residual map generated by an alignment system model, (iii) a substrate quality map including signals with varying intensities indicating the reliability of the alignment data, and / or (iv) a color difference map obtained by projecting a plurality of color laser beams onto the substrate, each color laser beam being reflected from an alignment mark on a layer of the current substrate, the reflected beams generating a diffraction pattern, the color difference map being a difference between a first diffraction pattern and a second diffraction pattern, the first diffraction pattern being associated with a first color of the plurality of color lasers, and the second diffraction pattern being associated with a second color of the plurality of color lasers; and / or

[0363] The leveling measurement data of the current substrate, the leveling measurement data comprising: (i) substrate height data, and / or (ii) the substrate height data converted into displacements in the x and y directions.

[0364] 48. The method of any one of clauses 38 to 47, wherein the performance data is an average overlay error value obtained by averaging overlay error values ​​associated with the previously patterned substrate.

[0365] 49. The method of any one of clauses 38 to 48, wherein the performance data is specific to each tool used in the semiconductor manufacturing process.

[0366] 50. The method of any one of clauses 38 to 49, wherein the overlay prediction model is configured to predict an overlay error caused by each tool used in a patterning process for the current substrate.

[0367] 51. The method of any one of clauses 38 to 50, wherein the tool used in the patterning process comprises: an etching apparatus; a photolithography apparatus; a chemical mechanical polishing apparatus, or a combination thereof.

[0368] 52. The method of any one of clauses 38 to 51, wherein the predicted overlay error comprises an overlay error caused by the etching apparatus, the lithography apparatus, the chemical mechanical polishing apparatus, or a combination thereof.

[0369] 53. A non-transitory computer readable medium comprising instructions that, when executed by one or more processors, result in operations comprising:

[0370] obtaining (i) performance data associated with a previously patterned substrate, and (ii) metrology data associated with a current substrate to be patterned;

[0371] executing an overlay prediction model using the metrology data associated with the current substrate to predict an overlay error caused by a tool used in a patterning process of the current substrate; and

[0372] Based on the performance data and the predicted overlay error, an overlay correction is determined to be applied to another tool at which the current substrate will be processed to compensate for the overlay error caused by the tool.

[0373] 54. The non-transitory computer readable medium of clause 53, wherein determining the overlay accuracy correction comprises:

[0374] combining the performance data with a predicted overlay error associated with the tool; and

[0375] A substrate adjustment is determined that minimizes the combined overlay error at another tool for the current substrate.

[0376] 55. The non-transitory computer-readable medium of any one of clauses 53 to 54, wherein the overlay accuracy prediction model is obtained by:

[0377] (i) performing a first principal component analysis (PCA) using alignment data associated with the previous patterned substrate or the test substrate, and (ii) performing a second PCA using overlay error data associated with the previous patterned substrate or the test substrate; and

[0378] A correlation is established between the components of the first PCA and the components of the second PCA.

[0379] 56. The non-transitory computer readable medium of clause 55, wherein the first PCA of the alignment data produces a first set of principal components that explains variations in the alignment data, wherein the first set of principal components includes a first set of basis functions and scores associated with the first set of basis functions.

[0380] 57. The non-transitory computer readable medium of clause 55, wherein the second PCA of the overlay error data produces a second set of principal components that explains variations in the overlay error data, wherein the second set of principal components includes a second set of basis functions and scores associated with the second set of basis functions.

[0381] 58. The non-transitory computer readable medium of clause 55, wherein the correlation between the first principal component and the second principal component converts alignment data for the current substrate into predicted overlay error data for the current substrate, the predicted overlay error data being associated with a particular process to which the current substrate will be subjected.

[0382] 59. The non-transitory computer readable medium of any one of clauses 53 to 58, wherein the measurement data comprises:

[0383] Alignment metrology data associated with the current substrate, the alignment metrology data comprising: (i) alignment sensor data, (ii) a residual map generated by an alignment system model, (iii) a substrate quality map including signals with varying intensities indicating the reliability of the alignment data, and / or (iv) a color difference map obtained by projecting a plurality of color laser beams onto the substrate, each color laser beam being reflected from an alignment mark on a layer of the current substrate, the reflected beams generating a diffraction pattern, the color difference map being a difference between a first diffraction pattern and a second diffraction pattern, the first diffraction pattern being associated with a first color of the plurality of color lasers, and the second diffraction pattern being associated with a second color of the plurality of color lasers; and / or

[0384] The leveling measurement data of the current substrate, the leveling measurement data comprising: (i) substrate height data, and / or (ii) the substrate height data converted into displacements in the x and y directions.

[0385] 60. The non-transitory computer readable medium of any of clauses 53 to 59, wherein the performance data is an average overlay error value obtained by averaging overlay error values ​​associated with the previously patterned substrate.

[0386] 61. The non-transitory computer readable medium of any of clauses 53 to 60, wherein the overlay prediction model is configured to predict an overlay error caused by each tool used in a patterning process for the current substrate.

[0387] 62. A system for overlay accuracy correction of a current substrate to be patterned, the system comprising:

[0388] Semiconductor manufacturing equipment;

[0389] a metrology tool for capturing metrology data associated with the current substrate to be patterned;

[0390] A processor configured to:

[0391] executing an overlay prediction model using the metrology data associated with the current substrate to predict an overlay error caused by the semiconductor manufacturing equipment used in a patterning process of the current substrate; and

[0392] An overlay correction is determined based on the performance data and the predicted overlay error to be applied to another tool where the current substrate will be processed to compensate for the overlay error caused by the tool.

[0393] 63. The system of clause 62, wherein the processor is configured to determine the overlay accuracy correction by:

[0394] combining the performance data with a predicted overlay error associated with the semiconductor manufacturing equipment; and

[0395] A substrate adjustment is determined that minimizes an overlay error of the combination at another semiconductor manufacturing tool used on the current substrate.

[0396] 64. The system of any one of clauses 62 to 63, wherein the processor is further configured to obtain the overlay accuracy prediction model by:

[0397] (i) performing a first principal component analysis (PCA) using alignment data associated with the previous patterned substrate or the test substrate, and (ii) performing a second PCA using overlay error data associated with the previous patterned substrate or the test substrate; and

[0398] A correlation is established between the components of the first PCA and the components of the second PCA.

[0399] 65. The system of clause 64, wherein the correlation between the first principal component and the second principal component converts the alignment data for the current substrate into predicted overlay error data for the current substrate, the predicted overlay error data being associated with a particular process to which the current substrate will be subjected.

[0400] 66. A system as described in any one of aspects 62 to 65, wherein the measurement data includes:

[0401] Alignment metrology data associated with the current substrate, the alignment metrology data comprising: (i) alignment sensor data, (ii) a residual map generated by an alignment system model, (iii) a substrate quality map including signals with varying intensities indicating the reliability of the alignment data, and / or (iv) a color difference map obtained by projecting a plurality of color laser beams onto the substrate, each color laser beam being reflected from an alignment mark on a layer of the current substrate, the reflected beams generating a diffraction pattern, the color difference map being a difference between a first diffraction pattern and a second diffraction pattern, the first diffraction pattern being associated with a first color of the plurality of color lasers, and the second diffraction pattern being associated with a second color of the plurality of color lasers; and / or

[0402] The leveling measurement data of the current substrate, the leveling measurement data comprising: (i) substrate height data, and / or (ii) the substrate height data converted into displacements in the x and y directions.

[0403] 67. The system of any of clauses 62 to 66, wherein the performance data is an average overlay error value obtained by averaging overlay error values ​​associated with the previously patterned substrates.

[0404] 68. The system of any one of clauses 62 to 67, wherein the semiconductor manufacturing equipment used in the patterning process comprises: an etching equipment; a photolithography equipment; a chemical mechanical polishing equipment, or a combination thereof.

[0405] 69. The system of any of clauses 62 to 68, wherein the overlay prediction model is configured to predict an overlay error caused by each tool used in a patterning process for the current substrate.

[0406] 70. A non-transitory computer readable medium having instructions thereon, which when executed by a computer cause the computer to:

[0407] obtaining first performance data associated with a portion of a plurality of patterned substrate layers of a substrate;

[0408] generating predicted performance data associated with one or more portions of a future layer to be formed on the substrate using the first performance data via a training model; and

[0409] Based on the first performance data associated with the patterned substrate layer and the predicted performance data associated with the future layer, values ​​for controlling one or more parameters of a patterning process are generated so that second performance data associated with the future layer of the substrate is within a specified performance range.

[0410] 71. The non-transitory computer readable medium of clause 70, wherein the first performance data comprises substrate level performance data associated with a current batch of patterned substrates.

[0411] 72. The non-transitory computer readable medium of clause 71, wherein the first performance data further comprises substrate level performance data associated with a previous batch of patterned substrates.

[0412] 73. The non-transitory computer readable medium of any of clauses 70 to 72, wherein the training model is configured to correlate the first performance data associated with a first layer with one or more other patterned substrate layers.

[0413] 74. The non-transitory computer readable medium of any one of clauses 70 to 73, wherein the first performance data comprises:

[0414] performance data associated with the first layer of the substrate; and

[0415] Another performance data associated with a second layer of the substrate, the second layer being located below the first layer of the substrate.

[0416] 75. The non-transitory computer readable medium of any of clauses 70 to 74, wherein the portion of the patterned substrate layer is aligned.

[0417] 76. The non-transitory computer readable medium of any one of clauses 70 to 75, wherein the instructions for generating the values ​​of the one or more parameters comprise:

[0418] determining uncorrected performance data associated with the patterned substrate layer based on the first performance data;

[0419] determining substrate level performance data for the future layer based on the predicted performance data associated with the one or more portions of the future layer;

[0420] The values ​​of one or more parameters of the patterning process are adjusted based on the substrate level performance data of the future layer and the uncorrected performance data of the patterned substrate layer so that the performance data of the future layer of the substrate is within the specified performance range after patterning.

[0421] 78. The non-transitory computer readable medium of any of clauses 70 to 77, wherein the portion of the substrate is a field, a sub-field, or a die region of the substrate.

[0422] 79. The non-transitory computer readable medium of any of clauses 70 to 78, wherein the first performance data including the substrate level performance data is divided into portion specific performance data.

[0423] 80. The non-transitory computer readable medium of any one of clauses 70 to 79, wherein the one or more parameters include: dose, focus, alignment of the substrate relative to a reference, height of the substrate, layer thickness, deposition process parameters, and / or etching process parameters.

[0424] 81. The non-transitory computer readable medium of any one of aspects 70 to 80, wherein the first performance data and the predicted performance data include at least one of the following:

[0425] overlay accuracy data associated with a given layer of the substrate;

[0426] alignment data associated with the given layer of the substrate;

[0427] leveling data associated with the given layer of the substrate;

[0428] correctable overlay error data associated with said given layer of said substrate, or

[0429] Height data of the given layer relative to one or more underlying layers on the substrate.

[0430] 82. The non-transitory computer-readable medium of any one of clauses 70 to 81, wherein the training model is at least one of: a linear model; or a machine learning model.

[0431] 83. The non-transitory computer-readable medium of clause 82, wherein the machine learning model is at least one of: a multilayer perceptron; a random forest; an adaptive boosted tree; a support vector regression; a Gaussian process regression; or a k-nearest neighbor algorithm.

[0432] 84. The non-transitory computer readable medium of clause 82, wherein the machine learning model is a high-level machine learning model comprising at least one of: a residual neural network (RNN); or a convolutional neural network (CNN).

[0433] 85. The non-transitory computer readable medium of clause 84, wherein the RNN model is formulated to include data associated with the patterned substrate layer as a time axis.

[0434] 86. One or more non-transitory computer-readable media storing a prediction model and instructions that, when executed by one or more processors, provide the prediction model, the prediction model being generated by:

[0435] obtaining performance data associated with portions of a plurality of patterned substrate layers formed one on top of another;

[0436] providing the performance data of the portion of the patterned substrate layer as input to a base prediction model to obtain predicted performance data associated with a portion of a first layer of the substrate; and

[0437] using the input performance data associated with the first layer as feedback to update one or more configurations of the base prediction model, wherein the one or more configurations are updated based on a comparison between the input performance data of the first layer and predicted performance data,

[0438] Therein, the predictive model is structured to correlate the performance data of the first layer with one or more other patterned substrate layers.

[0439] 87. The medium of aspect 86, wherein said obtaining said performance data comprises:

[0440] The performance data is grouped according to one or more portions of the substrate.

[0441] 88. The medium of any one of clauses 86 to 87, wherein training the model is an iterative process, each iteration comprising:

[0442] predicting, via the base prediction model, the performance data associated with the portion of the first layer using the performance data associated with the portion and given model parameter values;

[0443] comparing the model predicted performance data associated with the portion of the first layer with the obtained performance data associated with the portion of the first layer;

[0444] The given model parameter value of the base model is adjusted based on the difference so that a difference between the model-predicted performance data and the obtained performance data associated with the portion of the first layer of the plurality of patterned substrate layers is within a specified range.

[0445] 89. The medium of clause 88, wherein adjusting the given model parameter value of the model is performed until the difference is minimized.

[0446] 90. The medium of any of aspects 86 to 89, wherein the model is at least one of: a linear model; or a machine learning model.

[0447] 91. The medium of clause 90, wherein the machine learning model is at least one of: a multilayer perceptron; a random forest; an adaptive boosted tree; a support vector regression; a Gaussian process regression; or a k-nearest neighbor algorithm.

[0448] 92. The medium of clause 90, wherein the machine learning model is a high-level machine learning model comprising at least one of: a residual neural network (RNN); or a convolutional neural network (CNN).

[0449] 93. The medium of clause 92, wherein the RNN model is formulated to include patterned substrate layers of a current batch of substrates or patterned substrate layers of a previous batch of substrates as a time axis.

[0450] 94. The medium of any of clauses 86 to 93, wherein the portions of the patterned substrate layer are fields, sub-fields, or die regions of the substrate.

[0451] 95. The medium of any one of aspects 86 to 94, wherein the performance data comprises at least one of:

[0452] overlay accuracy data associated with a given layer of the substrate;

[0453] alignment data associated with the given layer of the substrate;

[0454] leveling data associated with the given layer of the substrate;

[0455] correctable overlay error data associated with said given layer of said substrate, or

[0456] Height data of the given layer relative to one or more underlying layers on the substrate.

[0457] Fig.231 is a block diagram illustrating a computer system 100 that can assist in implementing the methods, processes, or apparatus disclosed herein. The computer system 100 includes a bus 102 or other communication mechanism for communicating information, and a processor 104 (or multiple processors 104 and 105) coupled to the bus 102 for processing information. The computer system 100 also includes a main memory 106, such as a random access memory (RAM) or other dynamic storage device, coupled to the bus 102 for storing information and instructions to be executed by the processor 104. The main memory 106 can also be used to store temporary variables or other intermediate information during the execution of instructions to be executed by the processor 104. The computer system 100 also includes a read-only memory (ROM) 108 or other static storage device coupled to the bus 102 for storing static information and instructions for the processor 104. A storage device 110, such as a magnetic disk or optical disk, is provided and coupled to the bus 102 for storing information and instructions.

[0458] The computer system 100 can be connected to a display 112, such as a cathode ray tube (CRT) or a flat panel display or a touch panel display, via a bus 102 for displaying information to a computer user. An input device 114 including letter keys and other keys is connected to the bus 102 for communicating information and command selections to the processor 104. Another type of user input device is a cursor control 116, such as a mouse, trackball, or cursor direction keys, for communicating direction information and command selections to the processor 104 and for controlling cursor movement on the display 112. This input device typically has two degrees of freedom on two axes: a first axis (e.g., x) and a second axis (e.g., y), which allow the device to specify a position in a plane. A touch panel (screen) display can also be used as an input device.

[0459] According to one embodiment, portions of one or more methods described herein may be performed by computer system 100 in response to processor 104 executing one or more sequences of one or more instructions contained in main memory 106. Such instructions may be read into main memory 106 from another computer-readable medium, such as storage device 110. Execution of the sequence of instructions contained in main memory 106 causes processor 104 to perform the program steps described herein. One or more processors in a multi-processing configuration may also be used to execute the sequence of instructions contained in main memory 106. In alternative embodiments, hard-wired circuits may be used instead of or in combination with software instructions. Therefore, the description herein is not limited to any specific combination of hardware circuitry and software.

[0460] The term "computer-readable medium" as used herein refers to any medium that participates in providing instructions to the processor 104 for execution. This medium can take many forms, including but not limited to non-volatile media, volatile media, and transmission media. Non-volatile media include, for example, optical or magnetic disks, such as storage device 110. Volatile media include volatile memory, such as main memory 106. Transmission media include coaxial cables, copper wires, and optical fibers, including wires that contain bus 102. Transmission media can also take the form of sound waves or light waves, such as sound waves or light waves generated during radio frequency (RF) and infrared (IR) data communications. Common forms of computer-readable media include, for example, floppy disks, flexible disks, hard disks, magnetic tapes, any other magnetic media, CD-ROMs, DVDs, any other optical media, punch cards, paper tapes, any other physical media with hole patterns, RAM, PROMs and EPROMs, FLASH-EPROMs, any other memory chips or cartridges, carriers as described below, or any other medium that can be read by a computer.

[0461] Various forms of computer-readable media may be involved when carrying one or more sequences of one or more instructions to processor 104 for execution. For example, the instructions may initially be carried on a disk of a remote computer. The remote computer may load the instructions into its dynamic memory and send the instructions via a telephone line using a modem. A modem local to computer system 100 may receive data on a telephone line and use an infrared transmitter to convert the data into an infrared signal. An infrared detector connected to bus 102 may receive the data carried in the infrared signal and place the data on bus 102. Bus 102 carries the data to main memory 106, from which processor 104 retrieves and executes instructions. The instructions received by main memory 106 may optionally be stored on storage device 110 before or after execution by processor 104.

[0462] The computer system 100 may also include a communication interface 118 coupled to the bus 102. The communication interface 118 provides a bidirectional data communication connection to a network link 120, which is connected to a local area network 122. For example, the communication interface 118 may be an integrated services digital network (ISDN) card or a modem to provide a data communication connection to a corresponding type of telephone line. As another example, the communication interface 118 may be a local area network (LAN) card to provide a data communication connection to a compatible LAN. A wireless link may also be implemented. In any such implementation, the communication interface 118 sends and receives electrical, electromagnetic, or optical signals that carry digital data streams representing various types of information.

[0463] The network link 120 typically provides data communication to other data devices via one or more networks. For example, the network link 120 may provide a connection to a host computer 124 or to data equipment operated by an Internet Service Provider (ISP) 126 via a local area network 122. The ISP 126 in turn provides data communication services via a global data packet communication network (now commonly referred to as the "Internet") 128. Both the local area network 122 and the Internet 128 use electrical, electromagnetic or optical signals that carry digital data streams. The signals through the various networks and the signals on the network link 120 and through the communication interface 118 (which carry the digital data to and from the computer system 100) are exemplary forms of carrier waves that transport information.

[0464] The computer system 100 can send messages and receive data including program code via one or more networks, network link 120, and communication interface 118. In the Internet example, server 130 may transmit the requested program code for the application via Internet 128, ISP 126, local area network 122, and communication interface 118. For example, one such downloaded application can provide all or part of the method described herein. The received program code can be executed by processor 104 when it is received, and / or stored in storage device 110 or other non-volatile memory for later execution. In this way, computer system 100 can obtain application code in the form of a carrier wave.

[0465] Fig.24 An exemplary lithographic projection apparatus that may be utilized in conjunction with the techniques described herein is schematically depicted. The apparatus comprises:

[0466] - an illumination system IL for conditioning the radiation beam B. In this particular case, the illumination system further comprises a radiation source SO;

[0467] - a first platform (e.g. patterning device stage) MT provided with a patterning device holder for holding a patterning device MA (e.g. a reticle) and connected to a first positioner for accurately positioning the patterning device relative to the object PS;

[0468] - a second platform (substrate table) WT provided with a substrate holder for holding a substrate W (e.g. a resist coated silicon wafer) and connected to a second positioner for accurately positioning the substrate relative to the item PS;

[0469] - a projection system ("lens") PS (eg a refractive, reflective or catadioptric optical system) for imaging the illuminated portion of the patterning device MA onto a target portion C of the substrate W (eg comprising one or more dies).

[0470] As depicted herein, the device is of the transmissive type (i.e., has a transmissive patterning device). However, in general, the device may also be of, for example, the reflective type (have a reflective patterning device). The device may use a different kind of patterning device than a classical mask; examples include a programmable mirror array or an LCD matrix.

[0471] A source SO (e.g. a mercury lamp or an excimer laser, an LPP (laser produced plasma) EUV source) generates a radiation beam. This beam is fed into an illumination system (illuminator) IL, for example directly or after having traversed an adjustment member such as a beam expander Ex. The illuminator IL may comprise adjustment members AD for setting an outer radial extent and / or an inner radial extent (commonly referred to as σouter and σinner, respectively) of the intensity distribution in the beam. In addition, the illuminator IL will typically comprise a number of other components, such as an integrator IN and a condenser CO. In this way, the beam B impinging on the patterning device MA has a desired uniformity and intensity distribution in its cross section.

[0472] about Fig.24 It should be noted that the source SO can be within the housing of the lithographic projection apparatus (this is often the case when the source SO is, for example, a mercury lamp), but the source SO can also be remote from the lithographic projection apparatus, into which the radiation beam generated by the source SO is guided (for example, with the aid of suitable guiding mirrors); the latter situation is often the case when the source SO is an excimer laser (for example, based on KrF, ArF or F2 laser action).

[0473] The beam B then intercepts the patterning device MA which is held on the patterning device table MT. Having traversed the patterning device MA, the beam B passes through a lens PS which focuses the beam B onto a target portion C of the substrate W. With the aid of the second positioning means (and the interferometry means IF) the substrate table WT can be accurately moved, for example, so that a different target portion C is positioned in the path of the beam B. Similarly, the first positioning means can be used to accurately position the patterning device MA relative to the path of the beam B, for example after mechanical retrieval of the patterning device MA from a patterning device library or during a scan. Typically, the patterning device MA will be positioned with the aid of the second positioning means not in the patterning device library. Fig.24 Movement of the object tables MT, WT is achieved by a long-stroke module (coarse positioning) and a short-stroke module (fine positioning) explicitly depicted in FIG. 2. However, in the case of a stepper (as opposed to a step-and-scan tool), the patterning device table MT may be connected to the short-stroke actuator only, or may be fixed.

[0474] The depicted tools can be used in two different modes:

[0475] - in step mode, the patterning device table MT is kept substantially stationary and an image of the entire patterning device is projected once (i.e. a single "flash") onto a target portion C. The substrate table WT is then shifted in the x-direction and / or y-direction so that a different target portion C can be illuminated by the beam B;

[0476] - In scan mode, essentially the same situation applies, except that a given target portion C is not exposed in a single "flash". Instead, the patterning device table MT can be moved in a given direction (the so-called "scanning direction", e.g. the y-direction) at a speed v, so that the projection beam B is scanned over the image of the patterning device; in parallel, the substrate table WT is simultaneously moved in the same direction or in the opposite direction at a speed V=Mv, where M is the magnification of the lens PS (typically M=1 / 4 or 1 / 5). In this way, a relatively large target portion C can be exposed without having to compromise resolution.

[0477] Fig.25 Another exemplary lithographic projection apparatus 1000 that may be utilized in conjunction with the techniques described herein is schematically depicted.

[0478] The lithography projection apparatus 1000 comprises:

[0479] - Source collector module SO;

[0480] - an illumination system (illuminator) IL configured to condition a radiation beam B (e.g. EUV radiation);

[0481] - a support structure (eg, patterning device table) MT configured to support a patterning device (eg, mask or reticle) MA and connected to a first positioner PM configured to accurately position the patterning device;

[0482] - a substrate table (eg wafer stage) WT configured to hold a substrate (eg resist coated wafer) W and connected to a second positioner PW configured to accurately position the substrate; and

[0483] - a projection system (eg, a reflective projection system) PS configured to project the pattern imparted to the radiation beam B by the patterning device MA onto a target portion C of the substrate W (eg, comprising one or more dies).

[0484] As depicted here, the apparatus 1000 is of the reflective type (e.g., using a reflective patterning device). It should be noted that because most materials are absorptive in the EUV wavelength range, the patterning device can have a multilayer reflector including multiple stacks of, for example, molybdenum and silicon. In one example, the multilayer reflector has 40 layer pairs of molybdenum and silicon, where each layer is a quarter wavelength thick. X-ray lithography can be used to produce smaller wavelengths. Because most materials are absorptive at EUV and x-ray wavelengths, a thin piece of patterned absorbing material on the patterning device topography (e.g., a TaN absorber on top of a multilayer reflector) defines where features will be printed (positive resist) or not printed (negative resist).

[0485] Reference Fig.25 , the illuminator IL receives a beam of extreme ultraviolet radiation from a source collector module SO. Methods for generating EUV radiation include, but are not necessarily limited to, converting a material having at least one element (e.g., xenon, lithium, or tin) into a plasma state using one or more emission lines in the EUV range. In one such method, often referred to as laser produced plasma ("LPP"), a plasma may be generated by irradiating a fuel (e.g., a droplet, stream, or cluster of material having the line emitting element) with a laser beam. The source collector module SO may be a laser ( Fig.25 The laser is used to provide a laser beam for exciting the fuel. The resulting plasma emits output radiation, such as EUV radiation, which is collected using a radiation collector disposed in a source collector module. For example, when a CO2 laser is used to provide the laser beam for fuel excitation, the laser and the source collector module can be separate entities.

[0486] In such cases, the laser is not considered to form part of the lithographic apparatus, and the radiation beam is delivered from the laser to the source collector module by means of a beam delivery system including, for example, suitable guiding mirrors and / or a beam expander. In other cases, for example, when the source is a discharge produced plasma EUV generator (often referred to as a DPP source), the source may be an integral part of the source collector module.

[0487] The illuminator IL may include an adjuster for adjusting the angular intensity distribution of the radiation beam. Typically, at least the outer radial extent and / or the inner radial extent (commonly referred to as σouter and σinner, respectively) of the intensity distribution in a pupil plane of the illuminator may be adjusted. In addition, the illuminator IL may include various other components, such as a faceted field mirror device and a faceted pupil mirror device. The illuminator may be used to adjust the radiation beam to have a desired uniformity and intensity distribution in its cross-section.

[0488] The radiation beam B is incident on a patterning device (e.g. a mask) MA held on a support structure (e.g. a patterning device table) MT and is patterned by the patterning device. After reflection from the patterning device (e.g. a mask) MA, the radiation beam B passes through a projection system PS which focuses the beam onto a target portion C of a substrate W. With the aid of a second positioner PW and a position sensor PS2 (e.g. an interferometer device, a linear encoder or a capacitive sensor), the substrate table WT can be accurately moved, for example so that a different target portion C is positioned in the path of the radiation beam B. Similarly, a first positioner PM and a further position sensor PS1 can be used to accurately position the patterning device (e.g. a mask) MA relative to the path of the radiation beam B. The patterning device (e.g. a mask) MA and the substrate W can be aligned using patterning device alignment marks M1, M2 and substrate alignment marks P1, P2.

[0489] The depicted device 1000 may be used in at least one of the following modes:

[0490] 1. In step mode, the support structure (e.g. patterning device table) MT and the substrate table WT are kept substantially stationary (i.e. single static exposure) while the entire pattern imparted to the radiation beam is projected at one time onto a target portion C. The substrate table WT is then shifted in the X and / or Y direction so that a different target portion C can be exposed.

[0491] 2. In scan mode, the support structure (e.g. patterning device table) MT and the substrate table WT are scanned synchronously (i.e. single dynamic exposure) as a pattern imparted to the radiation beam is projected onto a target portion C. The speed and direction of the substrate table WT relative to the support structure (e.g. patterning device table) MT may be determined by the (de-)magnification and image reversal characteristics of the projection system PS.

[0492] 3. In another mode, the support structure (e.g. patterning device table) MT is kept substantially stationary, thereby holding the programmable patterning device, and the substrate table WT is moved or scanned, while a pattern imparted to the radiation beam is projected onto a target portion C. In this mode, a pulsed radiation source is typically used, and the programmable patterning device is updated as required after each movement of the substrate table WT or between successive radiation pulses during a scan. This mode of operation may be readily applicable to maskless lithography using a programmable patterning device, such as a programmable mirror array of the type mentioned above.

[0493] Fig.26The apparatus 1000 is shown in more detail and includes a source collector module SO, an illumination system IL, and a projection system PS. The source collector module SO is constructed and configured so that a vacuum environment can be maintained in an enclosure 220 of the source collector module SO. An EUV radiation emitting plasma 210 can be formed by a discharge-generated plasma source. EUV radiation can be generated by a gas or vapor (e.g., Xe gas, Li vapor, or Sn vapor) in which an extremely hot plasma 210 is generated to emit radiation in the EUV range of the electromagnetic spectrum. For example, the extremely hot plasma 210 is generated by a discharge that causes an at least partially ionized plasma. For efficient generation of radiation, a partial pressure of, for example, 10 Pa of Xe, Li, Sn vapor, or any other suitable gas or vapor may be required. In an embodiment, an excited plasma of tin (Sn) is provided to generate EUV radiation.

[0494] The radiation emitted by the hot plasma 210 is transferred from the source chamber 211 to the collector chamber 212 via an optional gas barrier or contaminant trap 230 (also referred to as a contaminant barrier or foil trap in some cases) positioned in or behind an opening in the source chamber 211. The contaminant trap 230 may include a channel structure. The contaminant trap 230 may also include a gas barrier, or a combination of a gas barrier and a channel structure. As is known in the art, the contaminant trap or contaminant barrier 230 further indicated herein includes at least a channel structure.

[0495] The collector chamber 212 may include a radiation collector CO which may be a so-called grazing incidence collector. The radiation collector CO has an upstream radiation collector side 251 and a downstream radiation collector side 252. Radiation traversing the collector CO may be reflected from the grating spectral filter 240 to be focused into a virtual source point IF along the optical axis indicated by the dotted line "O". The virtual source point IF is often referred to as an intermediate focus, and the source collector module is configured such that the intermediate focus IF is located at or near an opening 221 in the enclosure structure 220. The virtual source point IF is an image of the radiation emitting plasma 210.

[0496] The radiation then traverses an illumination system IL which may include a faceted field mirror device 22 and a faceted pupil mirror device 24 configured to provide a desired angular distribution of the radiation beam 21 at the patterning device MA, and a desired uniformity of radiation intensity at the patterning device MA. The radiation beam 21, after being reflected at the patterning device MA held by the support structure MT, forms a patterned beam 26, and the patterned beam 26 is imaged by the projection system PS via reflective assemblies 28, 30 onto a substrate W held by a substrate table WT.

[0497] More elements than shown may typically be present in the illumination optics unit IL and the projection system PS. Depending on the type of lithographic apparatus, a grating spectral filter 240 may optionally be present. In addition, more mirrors may be present than shown in the figures, for example, more than 100 mirrors may be present in the projection system PS. Fig.26 The reflective elements shown have 1 to 6 additional reflective elements.

[0498] like Fig.26 The collector optics CO illustrated in FIG. 1 is depicted as a nested collector with grazing incidence reflectors 253, 254 and 255, which is merely an example of a collector (or collector mirror). The grazing incidence reflectors 253, 254 and 255 are arranged axially symmetrically around the optical axis O, and this type of collector optics CO can be used in combination with a discharge produced plasma source, which is often referred to as a DPP source.

[0499] Alternatively, the source collector module SO may be as follows Fig. 27 Components of an LPP radiation system are shown. The laser LA is configured to deposit laser energy into a fuel such as xenon (Xe), tin (Sn), or lithium (Li), thereby producing a highly ionized plasma 210 with an electron temperature of tens of electron volts. High-energy radiation produced during the deexcitation and recombination of these ions is emitted from the plasma, collected by a near normal incidence collector optic CO, and focused onto an opening 221 in an enclosure 220.

[0500] The concepts disclosed herein can simulate or mathematically model any general imaging system for imaging sub-wavelength features, and can be used in particular for emerging imaging technologies that can produce shorter and shorter wavelengths. Emerging technologies already in use include EUV (extreme ultraviolet), DUV lithography that can produce wavelengths of 193 nm by using ArF lasers and even 157 nm by using fluorine lasers. In addition, EUV lithography can produce wavelengths in the range of 20 nm to 5 nm by using a synchrotron or by using high energy electrons incident on a material (solid or plasma) to produce photons in this range.

[0501] Although the concepts disclosed herein may be used for imaging on substrates such as silicon wafers, it should be understood that the disclosed concepts may be used with any type of lithography imaging system, such as a lithography imaging system for imaging on substrates other than silicon wafers.

[0502] The above description is intended to be illustrative rather than limiting. It will therefore be apparent to those skilled in the art that modifications may be made as described without departing from the scope of the claims set forth hereinafter.

Claims

1. A method for determining an overlay accuracy correction for a current substrate to be patterned, the method comprising: obtaining (i) performance data associated with a previously patterned substrate, and (ii) metrology data associated with the current substrate to be patterned; executing an overlay prediction model using the metrology data associated with the current substrate to predict an overlay error caused by a tool used in a patterning process of the current substrate; as well as Based on the performance data and the predicted overlay error, an overlay correction is determined to be applied to another tool at which the current substrate will be processed to compensate for the overlay error caused by the tool.

2. The method of claim 1, wherein: The performance data includes overlay error data of the previously patterned substrate.

3. The method of claim 2, wherein: Determining the overlay accuracy correction includes: combining the performance data with a predicted overlay error associated with the tool; and A substrate adjustment is determined that minimizes the combined overlay error at the other tool used in a patterning process of the current substrate.

4. The method of claim 3, wherein: The substrate adjustment comprises: the orientation of a substrate table on which the current substrate is mounted; and / or Leveling of the substrate table.

5. The method according to any one of claims 1 to 4, wherein: The overlay accuracy prediction model is obtained through the following operations: (i) performing a first principal component analysis (PCA) using alignment data associated with the previous patterned substrate or the test substrate, and (ii) performing a second principal component analysis using overlay error data associated with the previous patterned substrate or the test substrate; as well as A correlation is established between the components of the first principal component analysis and the components of the second principal component analysis.

6. The method of claim 5, wherein: The first principal component analysis of the alignment data produces a first set of principal components that explains variations in the alignment data, wherein the first set of principal components includes a first set of basis functions and scores associated with the first set of basis functions.

7. The method of claim 5, wherein: The second principal component analysis of the overlay error data produces a second set of principal components that explain variations in the overlay error data, wherein the second set of principal components includes a second set of basis functions and scores associated with the second set of basis functions.

8. The method of claim 7, wherein: One or more principal components of the second set of principal components account for overlay accuracy errors caused by a specific process or a specific tool of the patterning process.

9. The method of claim 5, wherein: The correlation between the first principal component and the second principal component converts the alignment data of the current substrate into predicted overlay error data of the current substrate, the predicted overlay error data being associated with a specific process to which the current substrate will be subjected.

10. The method according to any one of claims 1 to 4 and 6 to 9, wherein The measurement data include: Alignment metrology data associated with the current substrate, the alignment metrology data comprising: (i) alignment sensor data, (ii) a residual map generated by an alignment system model, (iii) a substrate quality map including signals with varying intensities indicating the reliability of the alignment data, and / or (iv) a color difference map obtained by projecting a plurality of color laser beams onto the substrate, each color laser beam being reflected from an alignment mark on a layer of the current substrate, the reflected beams generating a diffraction pattern, the color difference map being a difference between a first diffraction pattern and a second diffraction pattern, the first diffraction pattern being associated with a first color of the plurality of color lasers, and the second diffraction pattern being associated with a second color of the plurality of color lasers; and / or The leveling measurement data of the current substrate, the leveling measurement data comprising: (i) substrate height data, and / or (ii) the substrate height data converted into displacements in the x and y directions.

11. The method of any one of claims 1 to 4 and 6 to 9, wherein: The overlay prediction model is configured to predict an overlay error caused by each tool used in a patterning process on the current substrate.

12. The method of any one of claims 1 to 4 and 6 to 9, wherein: The tools used in the patterning process include: etching equipment; photolithography equipment; chemical mechanical polishing equipment, or a combination thereof.

13. The method of claim 12, wherein: The predicted overlay error includes an overlay error caused by the etching equipment, the photolithography equipment, the chemical mechanical polishing equipment, or a combination thereof.

14. A non-transitory computer readable medium comprising instructions that, when executed by one or more processors, result in operations comprising: obtaining (i) performance data associated with a previously patterned substrate, and (ii) metrology data associated with a current substrate to be patterned; executing an overlay prediction model using the metrology data associated with the current substrate to predict an overlay error caused by a tool used in a patterning process of the current substrate; as well as Based on the performance data and the predicted overlay error, an overlay correction is determined to be applied to another tool at which the current substrate will be processed to compensate for the overlay error caused by the tool.

15. A system for overlay accuracy correction of a current substrate to be patterned, the system comprising: Semiconductor manufacturing equipment; a metrology tool for capturing metrology data associated with the current substrate to be patterned; A processor configured to: executing an overlay accuracy prediction model using the metrology data associated with the current substrate to predict an overlay accuracy error caused by the semiconductor manufacturing equipment used in a patterning process of the current substrate; as well as An overlay correction is determined based on the performance data and the predicted overlay error to be applied to another tool where the current substrate will be processed to compensate for the overlay error caused by the tool.

Images