Method for generating characteristic pattern and training machine learning model
Through convolutional neural networks and generating machine learning models trained by adversarial networks, feature patterns and optical parameters are generated, which solves the problem of complex fine-tuning steps of lithography equipment under low k1 conditions, and improves the resolution and pattern of lithography equipment Reproduction accuracy meets the needs of modern semiconductor manufacturing.
Patent Information
- Application Number
- CN202410943928.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2018-10-17
- Filing Date
- 2019-10-08
- Publication Date
- 2024-11-08
AI Technical Summary
In lithography technology, existing lithography projection equipment is difficult to effectively manufacture independent functional components with a size far below 100nm. Especially in low k1 lithography, complex fine-tuning steps are difficult to reproduce the shape and size of the design layout, resulting in functional and performance challenges.
Using convolutional neural network (CNN) as the generator model, the machine learning model is trained by generating adversarial network (GAN), feature patterns are generated, optical proximity correction and manufacturability check are performed, and the design rules and optical during the patterning process are optimized. parameters to improve the printing accuracy of the pattern on the substrate.
The reproduction accuracy and functionality of patterns on the substrate under low k1 lithography conditions are improved, the resolution of lithography equipment is enhanced, and complex microstructures can be printed more accurately, meeting the needs of modern semiconductor manufacturing.
Smart Images

Figure CN118915395A_ABST
Abstract
Description
[0001] This application is a divisional of the international application PCT / EP2019 / 077146, which entered the Chinese national phase on April 16, 2021 and has application number 201980068610.6.
[0002] CROSS-REFERENCE TO RELATED APPLICATIONS
[0003] This application claims priority to U.S. Application No. 62 / 746,784, filed on October 17, 2018, the entire contents of which are incorporated herein by reference. Technical Field
[0004] The description herein generally relates to patterning processes and apparatus and methods for determining a pattern of features corresponding to a design layout. Background Art
[0005] A lithographic projection apparatus may be used, for example, to manufacture integrated circuits (ICs). In this case, a patterning device (e.g., a mask) may contain or provide a pattern corresponding to a single layer of the IC (a "design layout"), and the pattern may be transferred to a target portion (e.g., including one or more dies) on a substrate (e.g., a silicon wafer) on which a layer of radiation-sensitive material ("resist") has been coated, such as by irradiating the target portion through the pattern on the patterning device. In general, a single substrate contains a plurality of adjacent target portions to which the pattern is transferred successively, one 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; the 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 the reference direction. Different portions of the pattern on the patterning device are progressively transferred to one target portion. In general, since the lithographic projection apparatus will have a reduced 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. More information on lithographic apparatus as described herein can be gleaned, for example, from US 6,046,792, which is incorporated herein by reference.
[0006] Before the pattern is transferred from the pattern forming device to the substrate, the substrate can undergo various processes, such as primer coating, resist coating and soft baking. After exposure, the substrate can undergo other processes ("post-exposure processes"), such as post-exposure baking (PEB), development, hard baking and measurement / detection of the transferred pattern. This array of processes is used as the basis for manufacturing a single layer of a device (e.g., IC). The substrate can then undergo various processes, such as etching, ion implantation (doping), metallization, oxidation, chemical-mechanical polishing, etc., which are intended to refine a single layer of the device. If multiple layers are required in the device, the entire process or a variation thereof is repeated for each layer. Ultimately, the device will be present in each target portion on the substrate. These devices are then separated from each other by techniques such as dicing or sawing, whereby individual devices can be mounted on a carrier, connected to pins, etc.
[0007] Therefore, manufacturing devices (such as semiconductor devices) generally involves using multiple manufacturing processes to process substrates (e.g., semiconductor wafers) to form various features and multiple layers of the device. These layers and features are generally manufactured and processed using, for example, deposition, lithography, etching, chemical mechanical polishing, and ion implantation. Multiple devices can be made on multiple dies on a substrate, and then these devices are separated into individual devices. The device manufacturing process can be considered a patterning process. The patterning process involves a patterning step, such as optical and / or nanoimprint lithography using a pattern forming device in a lithographic device to transfer a pattern on the pattern forming device to a substrate, and the patterning process generally but optionally involves one or more related pattern processing steps, such as resist development by a developing device, baking of the substrate using a baking tool, etching of the pattern using an etching device, etc.
[0008] 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.
[0009] 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 pattern corresponding to a design layout onto a substrate using illumination from a deep ultraviolet illumination source, thereby producing individual functional elements having a size 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).
[0010] The process of printing features whose size is smaller than the classical resolution limit of a lithographic projection apparatus according to the resolution formula CD = k1 × λ / NA is generally referred to as low-k1 lithography, where λ is the wavelength of the radiation used (currently 248 nm or 193 nm in most cases), NA is the numerical aperture of the projection optics in the lithographic projection apparatus, CD is the "critical dimension" (usually the smallest feature size printed), and k1 is an empirical resolution factor. In general, the smaller k1 is, the more difficult it becomes to reproduce a pattern on a substrate that resembles the shape and size planned by the designer in order to achieve specific electrical functionality and performance. In order to overcome these difficulties, complex fine-tuning steps are applied to the lithographic projection apparatus, the design layout, or the patterning device. These fine-tuning steps include, for example, but are not limited to: optimization of NA and optical coherence settings, customized illumination schemes, use of phase-shifting patterning devices, optical proximity correction (OPC, sometimes also called "optical and process correction") in the design layout, or other methods generally defined as "resolution enhancement techniques" (RET). The term "projection optical element" as used herein should be broadly interpreted to cover various types of optical systems, including, for example, refractive optical elements, reflective optical elements, apertures, and reflective-refractive optical elements. The term "projection system" may also include components that operate according to any of these design types for guiding, shaping, or controlling a projection radiation beam uniformly or individually. The term "projection optical element" may include any optical component in a lithographic projection device, regardless of where the optical component is located on the optical path of the lithographic projection device. Projection optical elements may include optical components for shaping, adjusting, and / or projecting radiation from a source before the radiation passes through a pattern forming device, and / or optical components for shaping, adjusting, and / or projecting the radiation after the radiation passes through a pattern forming device. Projection optical elements typically do not include a source and a pattern forming device. Summary of the invention
[0011] According to an embodiment, a method for generating a feature pattern for a patterning process is provided. The method includes: obtaining a trained generator model and an input pattern, the trained generator model being configured to generate a feature pattern; and generating the feature pattern based on the input pattern via simulation of the trained generator model, wherein the input pattern is at least one of a random vector or a pattern class.
[0012] In an embodiment, the pattern of features is a patterning device pattern to be printed on the substrate subjected to the patterning process.
[0013] In an embodiment, the input pattern is obtained via simulation of a process model of a patterning process with a design layout as input resulting in a hotspot pattern.
[0014] In an embodiment, the process model includes an optical proximity correction model and a lithography manufacturability check model.
[0015] In an embodiment, the method further comprises: converting the feature pattern into a feature outline representation; applying a design rule check to the feature outline representation; and modifying the feature outline representation based on the design rule check to increase the likelihood that the feature pattern can be printed.
[0016] In an embodiment, converting the feature pattern includes: extracting contours of features within the feature pattern; and converting the contours into geometric shapes and / or Manhattanizing the feature pattern.
[0017] In an embodiment, the method further comprises: determining an optical proximity correction for a modified feature profile via simulation of the optical proximity correction model; determining a simulated pattern of the substrate corresponding to the modified feature profile via simulation of the process model of the patterning process.
[0018] In an embodiment, the method further comprises determining settings for the patterning process based on the feature pattern and / or the modified feature profile via simulation of the process model of the patterning process.
[0019] In an embodiment, the settings of the patterning process are values of process variables including dose, focus and / or optical parameters.
[0020] In an embodiment, the method further comprises: applying the setting of the patterning process via the lithography device to print the feature pattern on the substrate.
[0021] In an embodiment, the trained generator model is a convolutional neural network.
[0022] In an embodiment, the trained generator model is trained according to a machine learning training method called a generative adversarial network.
[0023] In an embodiment, the characteristic pattern and the input pattern are pixelated images.
[0024] In an embodiment, the input pattern comprises a design layout including a hotspot pattern.
[0025] In addition, the present disclosure provides a method for training a machine learning model for generating a feature pattern of a patterning process. The method includes: obtaining a machine learning model, the machine learning model including: (i) a generator model configured to generate a feature pattern to be printed on a substrate undergoing a patterning process, and (ii) a discriminator model configured to distinguish the feature pattern from a training pattern; and training the generator model and the discriminator model in a mutually cooperative manner based on a training set including the training pattern via a computer hardware system, so that the generator model generates the feature pattern matching the training pattern, and the discriminator model identifies the feature pattern as the training pattern, wherein the feature pattern and the training pattern include a hotspot pattern.
[0026] In an embodiment, the training is an iterative process, the iterations comprising: generating the feature pattern via simulation of the generator model with an input vector; evaluating a first cost function associated with the generator model; distinguishing the feature pattern from the training pattern via the discriminator model; evaluating a second cost function associated with the discriminator model; and adjusting parameters of the generator model to improve the first cost function, and adjusting parameters of the discriminator model to improve the second cost function.
[0027] In an embodiment, the input vector is a random vector and / or a seed hotspot image.
[0028] In an embodiment, the seed hotspot image is obtained from a simulation of a lithography process with a design layout as input.
[0029] In an embodiment, the distinguishing comprises: determining a probability that the characteristic pattern is the training pattern; and assigning a label to the characteristic pattern in response to the probability, the label indicating whether the characteristic pattern is a real pattern or a false pattern.
[0030] In an embodiment, in response to the probability exceeding a threshold, the characteristic pattern is marked as a true pattern.
[0031] In an embodiment, the first cost function comprises a first log-likelihood term which determines the probability that the characteristic pattern is false given the input vector.
[0032] In an embodiment, the parameters of the generator model are adjusted so that the first log-likelihood term is minimized.
[0033] In an embodiment, the second cost function includes a second log-likelihood term that determines the probability that the characteristic pattern is real given the training patterns.
[0034] In an embodiment, the second model parameters are adjusted such that the second log-likelihood term is maximized.
[0035] In an embodiment, the training pattern comprises a hotspot pattern.
[0036] In an embodiment, the training pattern is obtained from simulations of a process model of the patterning process, metrology data of printed substrates and / or a database storing printed patterns.
[0037] In an embodiment, the characteristic pattern includes features similar to the training pattern.
[0038] In an embodiment, the characteristic pattern and the training pattern further include a non-hotspot pattern and / or a user-defined pattern.
[0039] In an embodiment, the method further comprises generating, via simulation of the trained generator model, a design pattern comprising hotspot patterns and / or user-defined patterns.
[0040] In an embodiment, the generator model and the discriminator model are convolutional neural networks. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] The above aspects and other aspects and features will become apparent to those of ordinary skill in the art upon reviewing the following description of specific embodiments in conjunction with the accompanying drawings, in which:
[0042] Figure 1 shows a block diagram of various subsystems of a lithography system according to an embodiment;
[0043] Figure 2 shows exemplary categories of process variables according to an embodiment;
[0044] Figure 3 is a flow chart for modeling and / or simulating a portion of a patterning process according to an embodiment;
[0045] Figure 4 A flow chart showing a method for determining the presence of defects in a lithography process according to an embodiment;
[0046] Figure 5 is a schematic diagram of a method for generating a hotspot pattern based on machine learning according to an embodiment;
[0047] Figure 6 is a flow chart of a method for generating a feature pattern for a patterning process according to an embodiment;
[0048] Figure 7 An overview of the training process of a machine learning model based on a generative adversarial network architecture according to an embodiment is described;
[0049] Figure 8 It is training according to the embodiment Figure 6 A flowchart of an exemplary method of a generator model of
[0050] Fig. 9A is an example of a real pattern printed on a substrate according to an embodiment;
[0051] Fig. 9B According to the embodiment, Figure 7 The trained generator model generates the corresponding Fig. 9A Examples of characteristic patterns of;
[0052] Fig.10 Exemplary deficiencies according to embodiments and exemplary ways to solve the deficiencies are described;
[0053] Fig.11 is a block diagram of an example computer system according to an embodiment;
[0054] Fig.12 is a schematic diagram of a lithographic projection apparatus according to an embodiment;
[0055] Fig.13 is a schematic diagram of another lithographic projection apparatus according to an embodiment;
[0056] Fig.14 According to the embodiment Fig.12 A more detailed view of the devices in
[0057] Fig.15 According to the embodiment Fig.13 and Fig.14 A more detailed view of the source collector module SO of the device. DETAILED DESCRIPTION
[0058] Before describing the embodiments in detail, it is instructive to present an exemplary environment in which the embodiments may be implemented.
[0059] Although specific reference may be made herein to IC manufacturing, it should be clearly understood that the description herein has many other possible applications. For example, it may be used to manufacture integrated optical systems, guide and detect patterns for magnetic domain memory, liquid crystal display panels, thin film magnetic heads, etc. It will be understood by those skilled in the art that in the context of such 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.
[0060] 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 extreme ultraviolet radiation (EUV, e.g., having a wavelength in the range of about 5 to 100 nm).
[0061] The pattern forming device may include or may form one or more design layouts. The design layout may be generated using a computer-aided design (CAD) program, a process often referred to as electronic design automation (EDA). 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 of device manufacturing is to faithfully reproduce the original design intent (via the pattern forming device) on the substrate.
[0062] As an example, pattern layout design may include the application of resolution enhancement techniques such as optical proximity correction (OPC). OPC deals with the fact that the final size and placement of the image of the design layout projected on the substrate will be different from or simply dependent 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 in this article. 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, not necessarily using a physical pattern forming device, but using a design layout to represent a physical pattern forming device. For small feature sizes and high feature densities on some design layouts, the location 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 arise from trace amounts of radiation coupled from one feature to another or non-geometric optical effects such as diffraction and interference. Similarly, proximity effects can arise from diffusion and other chemical effects during post-exposure baking (PEB), resist development, and etching, which usually follows lithography.
[0063] To increase the chance that the projected image of the design layout is in accordance with the requirements of a given target circuit design, complex numerical models, corrections, or pre-distortions of the design layout can be used to predict and compensate for proximity effects. The paper "Full-Chip Lithography Simulation and Design Analysis-How OPC Is Changing IC Design" (C. Spence, Proc. SPIE, Vol. 5751, pp. 1-14 (2005)) provides an overview of current "model-based" optical proximity correction procedures. In a typical high-end design, almost every feature of the design layout has some modifications in order to achieve high fidelity of the projected image to the target design. These modifications can include shifts or offsets of edge positions or line widths, as well as the application of "auxiliary" features intended to assist the projection of other features.
[0064] Assist features can be considered the difference between features on the patterning device and features in the design layout.The terms "main feature" and "assist feature" do not imply that a particular feature on the patterning device must be labeled as a main feature or an assist feature.
[0065] The terms "mask" or "patterning device" as used herein may be broadly interpreted as referring to a general patterning device that can be used to impart a patterned cross-section to an incident radiation beam, the patterned cross-section corresponding to the pattern to be generated in a target portion of the substrate; the term "light valve" may also be used in this context. In addition to classical masks (transmissive or reflective; binary, phase-shift, hybrid, etc.), examples of other such patterning devices include:
[0066] - A programmable mirror array. An example of this device is a matrix-addressable surface with a viscoelastic control layer and a reflective surface. The basic principle behind this apparatus is, for example: addressed areas of the reflective surface cause incident radiation to be reflected as diffracted radiation, while non-addressed areas cause incident radiation to be reflected as non-diffracted radiation. Using appropriate filters, this non-diffracted radiation can be filtered out from the reflected beam, leaving only the diffracted radiation; in this way, the beam is patterned according to the addressing pattern of the matrix-addressable surface. Appropriate electronic components can be used to perform the desired matrix addressing.
[0067] - Programmable LCD array. An example of this type of construction is given in US Pat. No. 5,229,872, which is incorporated herein by reference.
[0068] As a brief introduction, 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 an extreme ultraviolet (EUV) source (as discussed above, the lithographic projection apparatus itself need not have a radiation source), and illumination optics that, for example, define a partial coherence (expressed as sigma) and may include optical elements 14A, 16Aa, and 16Ab that shape the radiation from source 12A; a patterning device 18A; and a transmissive optical element 16Ac that projects an image of a pattern of the patterning device onto a substrate plane 22A. An adjustable filter or aperture 20A at a pupil plane of the projection optics may define a range of beam angles impinging on the substrate plane 22A, wherein the maximum possible angle defines the numerical aperture NA=n sin(θ ) of the projection optics. max ), where n is the refractive index of the medium between the substrate and the final 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.
[0069] In a lithographic projection apparatus, a source provides irradiation (i.e., radiation) to a pattern forming device, and a projection optical element guides and shapes the irradiation onto a substrate via the pattern forming device. The projection optical element 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 serve as a latent "resist image" (RI) therein. A resist image (RI) may be defined as the 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 pattern forming device, and the projection optical element) specify the aerial image. Since a patterning device used in a lithographic projection apparatus may 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.
[0070] Although specific reference may be made herein to the use of lithographic equipment in IC manufacturing, it should be understood that the lithographic equipment described herein may have other applications, such as manufacturing integrated optical systems, guidance and detection patterns for magnetic domain memories, liquid crystal displays (LCDs), thin film magnetic heads, etc. It will be appreciated by those skilled in the art that in the context of these alternative applications, any use of the term "wafer" or "die" herein may be considered synonymous with the more general term "substrate" or "target portion", respectively. The substrates referred to herein may be processed in, for example, a track (a tool that typically applies a resist layer to a substrate and develops the exposed resist) or a measurement tool or an inspection tool before or after exposure. Where applicable, the disclosure herein may be applied to these and other substrate processing tools. In addition, the substrate may be processed more than once, for example, to generate a multi-layer IC, so that the term "substrate" used herein may also refer to a substrate that already contains multiple processed layers.
[0071] The terms "radiation" and "beam" as used herein encompass all types of electromagnetic radiation, including ultraviolet (UV) radiation (e.g. having a wavelength of 365, 248, 193, 157 or 126 nm) and extreme ultraviolet (EUV) radiation (e.g. having a wavelength in the range of 5 to 20 nm), as well as particle beams, such as ion beams or electron beams.
[0072] Various patterns on or provided by a pattern forming device may have different process windows, i.e., the space of process variables according to which patterns will be generated within specifications. Examples of pattern specifications for potential systematic defects include checking for necking, line pullback, line thinning, CD, edge placement, overlap, resist top loss, resist undercut and / or bridging. The process windows of all patterns on a pattern forming device or a region thereof may be obtained by merging the process windows of each individual pattern (e.g., overlapping the process windows). The boundaries of the process windows of all patterns contain the boundaries of the process windows of some of the individual patterns. In other words, these individual patterns limit the process windows of all patterns. These patterns may be referred to as "hot spots" or "process window limiting patterns (PWLP)", and "hot spots" and "process window limiting patterns (PWLP)" may be used interchangeably herein. When controlling a portion of a patterning process, it is possible and economical to focus on hot spots. When there are no defects in the hot spots, it is most likely that all patterns are defect-free.
[0073] In an embodiment, a simulation-based method has been developed to verify the correctness of the design and mask layout before manufacturing the mask. One such method is described in U.S. Pat. No. 7,003,758, entitled "System and Method for Lithography Simulation", the subject of which is incorporated herein by reference in its entirety and is referred to herein as a "simulation system". Even with the best possible RET implementation and verification, it is still impossible to optimize every feature of the design. Some structures are often not properly corrected due to technical limitations, implementation errors, or conflicts with adjacent features. The simulation system can identify specific features of the design that will result in an unacceptably small process window or excessive critical dimension (CD) changes within the usual expected distance of the processing conditions, such as focus and exposure changes. These defective areas must be corrected before making the mask. However, even in the best design, there will be structures or structural parts that cannot be optimally corrected. Although these weak areas may generate good chips, they may have an acceptable process window to a minimum and may be in the part of the device that will most likely fail under changing processing conditions (due to changes in wafer processing conditions, mask processing conditions, or a combination of both). These weak areas are referred to herein as "hot spots".
[0074] The variables of the patterning process are called “process variables.” The term process variables may also be interchangeably referred to as “patterning process parameters” or “process parameters.” The patterning process may include processes both upstream and downstream of the actual transfer of the pattern in the lithographic apparatus. Figure 2Exemplary categories of process variables 370 are shown. The first category may be variables 310 of a lithographic apparatus or any other apparatus used in a lithographic process. Examples of this category include variables such as the irradiation element, projection system, substrate stage, etc. of the lithographic apparatus. The second category may be variables 320 of one or more processes performed during the patterning process. Examples of this category include focus control or focus measurement, dose control or dose measurement, bandwidth, exposure duration, development temperature, chemical composition used in development, etc. The third category may be variables 330 of the design layout and its implementation in or using a patterning device. Examples of this category may include the shape and / or location of assist features, adjustments applied by resolution enhancement technology (RET), CD of mask features, etc. The fourth category may be variables 340 of the substrate. Examples include characteristics of structures below the resist layer, chemical composition and / or physical dimensions of the resist layer, etc. The fifth category may be characteristics of time variations of one or more variables of the patterning process 350. 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 mechanisms used to adjust the underlying variables (e.g., stage position, laser intensity). A sixth category may be characteristics 360 of processes upstream or downstream of pattern transfer in the lithographic apparatus, such as spin coating, post-exposure bake (PEB), development, etching, deposition, doping, and / or packaging.
[0075] 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. These parameters often express errors from 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.).
[0076] The values of some or all of the process variables or parameters related thereto may be determined by appropriate 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 such as level sensors or alignment sensors of a lithographic apparatus, control systems of a lithographic apparatus (e.g., substrate or patterning device stage control systems), sensors in a track tool, etc.). The values may come from an operator of the patterning process.
[0077] exist Figure 3An exemplary flow chart for modeling and / or simulating portions of a patterning process is illustrated in . As will be appreciated, the models may represent different patterning processes and need not include all of the models described below. Source model 1200 represents the optical characteristics of the illumination of the patterning device (including the radiation intensity distribution, bandwidth, and / or phase distribution). Source model 1200 may represent the optical characteristics of the illumination, including but not limited to numerical aperture settings, illumination sigma (σ) settings, and any particular illumination shape (e.g., off-axis radiation shapes such as toroidal, quadrupole, dipole, etc.), where σ (or sigma) is the outer radial extent of the illuminator.
[0078] The projection optical element model 1210 represents the optical properties of the projection optical element (including the changes to the radiation intensity distribution and / or phase distribution caused by the projection optical element). The projection optical element model 1210 can represent the optical properties of the projection optical element, which include aberrations, distortions, one or more refractive indices, one or more physical dimensions, one or more physical dimensions, etc.
[0079] The patterning device / design layout model module 1220 captures the manner in which design features are laid out in the pattern of the patterning device, and may include a representation of detailed physical properties of the patterning device as described, for example, in U.S. Pat. No. 7,587,704, which is incorporated herein by reference in its entirety. In an embodiment, the patterning device / design layout model module 1220 represents the optical properties (including changes in the radiation intensity distribution and / or phase distribution generated by a given design layout) of a design layout (e.g., a device design layout corresponding to features of an integrated circuit, memory, electronic device, etc.), which is a representation of the arrangement of features on or by the patterning device. Since the patterning device used in the lithographic projection apparatus can be changed, it is necessary to separate the optical properties of the patterning device from the optical properties of the rest of the lithographic projection apparatus, including at least the illumination and projection optical elements. The goal of the simulation is often to accurately predict, for example, edge placement and CD, which can then be compared to the device design. The device design is typically defined as a pre-OPC patterning device layout and will be provided in a standardized digital file format such as GDSII or OASIS.
[0080] An aerial image 1230 may be simulated by a source model 1200, a projection optics model 1210, and a patterning device / design layout model 1220. The aerial image (AI) is the radiation intensity distribution at the substrate level. The optical properties of the lithographic projection apparatus (e.g., the properties of the illuminator, the patterning device, and the projection optics) determine the aerial image.
[0081] A resist layer on a substrate is exposed by an aerial image, and the aerial image is transferred to the resist layer as a latent image "resist image" (RI) therein. A resist image (RI) can be defined as the spatial distribution of the solubility of the resist in the resist layer. A resist image 1250 can be simulated from an aerial image 1230 using a resist model 1240. A resist model can be used to calculate a resist image from an aerial image, an example of which can be found in U.S. Patent Application Publication No. US2009-0157360, the entire disclosure of which is incorporated herein by reference. A resist model typically describes the effects of chemical processes occurring during resist exposure, post-exposure baking (PEB), and development, in order to predict, for example, the profile of a resist feature formed on a substrate, and is therefore typically only related to these properties of the resist layer (e.g., the effects of chemical processes occurring during exposure, post-exposure baking, and development). In an embodiment, the optical properties of the resist layer (eg, refractive index, film thickness, propagation and polarization effects) may be acquired as part of the projection optics model 1210 .
[0082] Thus, in general, the connection between the optical model and the resist model is the simulated spatial image intensity within the resist layer, which results from the projection of the radiation onto the substrate, refraction at the resist interface, and multiple reflections in the resist film stack. The radiation intensity distribution (spatial image intensity) is transformed into a latent "resist image" by absorption of the incident energy, which is further modified by diffusion processes and various loading effects. Efficient simulation methods that are fast enough for full-chip applications approximate the actual three-dimensional intensity distribution in the resist stack by a two-dimensional spatial (and resist) image.
[0083] In an embodiment, the resist image may be used as an input to a post-pattern transfer process model module 1260. The post-pattern transfer process model 1260 defines the performance of one or more post-resist development processes (eg, etching, developing, etc.).
[0084] The simulation of the patterning process can, for example, predict the profile in the resist and / or etched image, CD, edge placement (e.g., edge placement error), etc. Thus, 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 can be compared to the desired design to, for example, correct the patterning process, identify locations where defects are predicted to occur, etc. The desired design is typically defined as a pre-OPC design layout that can be provided in a standardized digital file format such as GDSII or OASIS or other file formats.
[0085] Thus, the model formulation describes most, if not all, of the known physics and chemistry of the overall process, and each of the model parameters ideally corresponds to a distinct physical or chemical effect. Thus, the model formulation sets an upper limit on how well the model can be used to simulate the overall manufacturing process.
[0086] Figure 4 A flow chart of a method for determining the presence of defects in a lithography process according to an embodiment is shown. In process P411, a hot spot or a portion thereof is identified based on a pattern (e.g., a pattern on a pattern forming device) using any suitable method. For example, a hot spot can be identified by analyzing a pattern on a pattern using an empirical model or a computational model. In an empirical model, an image of a pattern (e.g., a resist image, an optical image, an etching image) is not simulated; instead, the empirical model predicts a defect or the probability of a defect based on a correlation between a processing parameter, a parameter of the pattern, and the defect. For example, the empirical model can be a classification model or a database of defect-prone patterns. In a computational model, a portion or characteristic of an image is calculated or simulated, and a defect is identified based on the portion or the characteristic. For example, a line pullback defect can be identified by finding a line end that is too far away from the desired location; a bridging defect can be identified by finding a location where two lines are not ideally joined; an overlapping defect can be identified by finding two features on a separation layer that are not ideally overlapped or not ideally overlapped. Empirical models are generally less computationally expensive than computational models. The process window of the hotspot can be determined based on the hotspot location and process window of the individual hotspot and / or the process window of the hotspot can be compiled into a map - that is, a process window that varies depending on the location is determined. The process window map can characterize the layout-specific sensitivity and processing margin of the pattern. In another example, the hotspot, its location and / or its process window can be determined experimentally, such as by FEM wafer inspection or appropriate measurement tools. Defects can include those defects that cannot be detected in post-development inspection (ADI) (usually optical inspection), such as resist top loss, resist undercut, etc. Conventional inspection only reveals these defects after the substrate is irreversibly processed (e.g., etched), at which time the wafer cannot be reprocessed. Therefore, at the time of drafting this document, it is not possible to detect these resist top loss defects using current optical technology. However, simulations can be used to determine where resist top loss can occur and to what extent the severity will be. Based on this information, a decision can be made to use a more accurate inspection method (and typically more time consuming) to detect a particular possible defect to determine if the defect requires rework, or a decision can be made to rework the imaging of a particular resist layer (remove the resist layer with the resist top loss defect and re-coat the wafer to re-image that particular layer) before performing an irreversible process (e.g., etching).
[0087] In process P412, the processing parameters according to which the hotspot is processed (e.g., imaged or etched onto the substrate) are determined. The processing parameters may be local—depending on the location of the hotspot, the location of the die, or both. The processing parameters may be global—independent of the location of the hotspot and the die. An exemplary way to determine the processing parameters is to determine the state of the lithographic equipment. For example, the laser bandwidth, focus, dose, source parameters, projection optical element parameters, and spatial or temporal variations of these parameters may be measured from the lithographic equipment. Another exemplary way is to infer the processing parameters from data obtained from measurements performed on the substrate or from an operator of the processing equipment. For example, the measurement may include detecting the substrate using a diffraction tool (e.g., ASML YieldStar), an electron microscope, or other appropriate inspection tool. Processing parameters for any location on the processed substrate (including the identified hotspot) may be obtained. The processing parameters may be compiled into a map that varies according to the location—lithographic parameters or process conditions. Of course, other processing parameters may be represented as varying according to the location, i.e., a map. In an embodiment, the processing parameters may be determined before and preferably immediately before each hotspot is processed.
[0088] In process P413, the presence, probability of presence, characteristics, or a combination thereof of a defect at the hotspot is determined using the processing parameters based on which the hotspot is processed. The determination can be as simple as comparing the processing parameters to the process window of the hotspot—if the processing parameters fall within the process window, then there are no defects; if the processing parameters fall outside the process window, then at least one defect is expected to exist. It can also be determined using an appropriate empirical model (including a statistical model). For example, a classification model can be used to provide the probability of the presence of a defect. Another way to make this determination is to use a computational model to simulate an image or expected patterned profile of the hotspot under the processing parameters and measure the image or profile parameters. In an embodiment, the processing parameters can be determined immediately after processing a pattern or substrate (i.e., before processing a pattern or the next substrate). The determined presence and / or characteristics of a defect can be used as a basis for a decision to dispose (rework or accept). In an embodiment, the processing parameters can be used to calculate a moving average of the lithography parameters. The moving average is used to capture long-term drifts in the lithography parameters without being disturbed by short-term fluctuations.
[0089] In an embodiment, hot spots are detected based on simulated images of patterns on substrates. Once the simulation of the patterning process (e.g., including OPC and manufacturability checks such as process models) is completed, potential weaknesses that change with process conditions in the design, i.e., hot spots, can be calculated according to one or more definitions (e.g., certain rules, thresholds, or indicators). Hot spots can be determined based on the following: absolute CD value, CD relative to the rate of change of one or more of the parameters that change in the simulation ("CD sensitivity"), the slope of the spatial image intensity or NILS (i.e., "edge slope" or "normalized image logarithmic slope", usually abbreviated as "NILS", which indicates the lack of clarity or image blur), wherein the edge of the resist feature is expected (calculated according to a single threshold / bias model or a more complete resist model). Alternatively, hot spots can be determined based on a set of predetermined rules such as those used in a design rule checking system, the predetermined rules including but not limited to line end pullback, corner rounding, proximity to adjacent features, pattern necking or contraction, and other indicators of pattern deformation relative to the desired pattern. CD sensitivity to small changes in mask CD is a particularly important lithography parameter known as MEF (Mask Error Factor) MEEF (Mask Error Enhancement Factor). Calculation of MEF relative to focus and exposure provides a critical indicator of the probability that mask process variations convoluted by wafer process variations will result in unacceptable pattern degradation of a particular pattern element. Hotspots can also be identified based on variations in overlay error relative to underlying or subsequent process layers and CD variations, or by sensitivity to variations in overlay and / or CD between exposures in a multi-exposure process.
[0090] As semiconductor manufacturing proceeds to the next technology node (such as a single-digit nm node), design patterns are used to drive improvements in process accuracy, stability, and predictability. Manufacturing facilities are always looking for ways to improve the cycle time of their IC manufacturing. In the early stages of the development cycle, the full chip design at the new node does not exist, but there will be a standard cell library and a very small cell block. In order to increase its pattern coverage, manufacturers build their own model proofing (mock-up) patterns through design reduction or a custom pattern creation method. After the first pass of the model and patterning process matching scheme are generated, an early understanding of hot spots and non-hot spots patterns can be formed. Such patterns are valuable for driving improvements in simulation models, design rules, OPC and verification matching schemes, as well as source irradiation and mask optimization. Ultimately, manufacturers will have a pattern set that is more likely to represent the desired pattern or design layout, but it may take several years to achieve this goal.
[0091] Manufacturers do not have sufficient pattern information early in the process development cycle, thereby hindering their ability to more rapidly increase their learning and development rates.
[0092] Today's methods for generating patterns soon after new technology nodes emerge result in many unrealistic patterns compared to what will ultimately be encountered on real substrates when they are printed. New patterns generated via existing methods cannot be commanded to generate only hotspot patterns or only non-hotspot patterns, resulting in an unfavorable software processing overhead (e.g., in terms of time, memory, resources, etc.) to properly validate the newly created patterns.
[0093] Figure 5 The invention provides an overview of the method for generating feature patterns (e.g., hotspot patterns) based on machine learning described herein. According to the method of the present disclosure, a generator model is trained to generate feature patterns such as hotspot patterns, distinguish whether the feature patterns are hotspot patterns or non-hotspot patterns, and further verify the feature patterns with respect to design rule checking (DRC). The feature patterns (e.g., hotspot patterns) are verified and stored in a hotspot database. The hotspot patterns can be used for different purposes during the early stages of the patterning process, specifically, for mask layout design and determining the optimal settings of the equipment of the patterning process.
[0094] In an embodiment, a training set including hotspot patterns 501a and non-hotspot patterns 501b may be obtained for initial training of a machine learning model including a generator model and a discriminator model discussed in more detail later in this disclosure. The training set may be provided as a feature vector in a GDS format. In an embodiment, tags (e.g., hotspots, non-hotspots, etc.) may also be included in the training set.
[0095] In process P501, a training set having patterns 501a and 501b is input to a machine learning model. Process P501 involves training the Figure 6 The generator model and discriminator model discussed in detail. During the training process, multiple feature patterns can be generated by the generator model. Then, the discriminator model can identify a subset of these feature patterns as hotspot patterns, another subset as non-hotspot patterns, and another subset can be other patterns to be ignored. In addition, process P501 involves performing DRC rule checks on a subset of feature patterns (e.g., a subset of hotspot patterns). Within this subset, only specific patterns can satisfy DRC (e.g., patterns marked with circles in 510), while some patterns fail the check (e.g., patterns marked with crosses in 510). At the same time, some other patterns can be ignored because these patterns do not qualify as hotspot patterns or non-hotspot patterns.
[0096] In process P503, a subset of feature patterns that are identified as hotspot patterns and satisfy the DRC can be stored in a database. Thus, a hotspot pattern database is established that can be used for various applications in the patterning process.
[0097] Figure 6 is a flow chart of a method for generating a feature pattern for a patterning process. The method involves: generating a feature pattern (e.g., a hotspot pattern) for early design and development of a design pattern, a mask pattern; and / or determining settings for one or more devices used in a patterning process (e.g., optimal values for dose, focus, etc.) or values for different parameters of a patterning process. In an embodiment, a plurality of feature patterns may be generated using a trained generator model configured to generate a feature pattern (e.g., a mask layout). Such feature patterns, such as a hotspot pattern or a set of hotspot patterns, are critical for setting a patterning process, for example, when defining a new technology node (e.g., less than 10 nm) or defining a new, more complex design layout. In an embodiment, the feature pattern and the input pattern may be represented as a pixelated image, a vector representation of the intensity of each pixel of the pixelated image, or other image-related formats used in image processing.
[0098] In process P611 , the method involves obtaining a trained generator model 601 configured to generate a feature pattern, and an input pattern 603 .
[0099] In an embodiment, a feature pattern is any patterning device pattern (e.g., a mask pattern) that can be used to design a pattern on a substrate for a new technology node. In an embodiment, a feature pattern is a predicted pattern that can potentially be printed on a substrate undergoing a patterning process. The predicted pattern can be determined (e.g., via simulation) based on, for example, a reduction in a design layout. In an embodiment, a feature pattern may be one or more hotspot patterns or a pattern similar to a hotspot pattern previously printed on a substrate undergoing a patterning process. In an embodiment, a feature pattern may be one or more patterns that are geometrically different from a hotspot pattern. In an embodiment, a feature pattern may be a pattern that satisfies a design rule check and / or a lithography manufacturability check.
[0100] The trained generator model 601 is a machine learning model trained to generate a characteristic pattern. The training can be based on a training set including a sample (or multiple samples) of a hotspot pattern and / or a label indicating whether the characteristic pattern is a hotspot pattern or a non-hotspot pattern. The trained generator model 601 can also be trained to label the generated pattern (i.e., the characteristic pattern). The label can indicate whether the generated model is a hotspot pattern, a non-hotspot pattern, a user-defined pattern, or a pattern of other classes of interest (e.g., a pattern with the highest density, frequency of occurrence, a measurement pattern).
[0101] In an embodiment, the trained generator model 601 is a convolutional neural network (CNN). The convolutional neural network is constrained, for example, in terms of weight and bias values, number of layers, cost function, and other model parameters that are modified during the training of the CNN. Therefore, the CNN is a specific model trained based on a specific training data set including, for example, hot spot patterns. Depending on the training method, the trained generator model 601 can have different structures, weights, biases, etc. Figure 6 An exemplary training method for training a machine learning model (e.g., CNN) is discussed. In an embodiment, the trained generator model 601 is trained according to a training method known as a generative adversarial network. Training based on a generative adversarial network includes two machine learning models trained together so that the generator model gradually generates more accurate and robust results.
[0102] In an embodiment, the trained generator model 601 may take as input, for example, a design layout with hot spots or a random vector, and generate a pattern in the form of a pixelated image represented in, for example, a GDS format.
[0103] The input pattern 603 may be a random vector, a pattern of a particular type of pattern (e.g., contact holes, strips, or a combination thereof), a design layout, and / or a reduced version of a previous design layout (e.g., obtained by scaling down one or more features of a previous design layout). In an embodiment, the input pattern is obtained via simulation of a process model of a patterning process that results in a hotspot pattern with the design layout as input. Thus, based on the type of pattern of interest, the trained generator model may predict a corresponding feature pattern. In an embodiment, the input pattern may be any input that indicates a type of pattern that may be used to generate a hotspot pattern.
[0104] In addition, in process P613, the method involves generating a feature pattern 613 based on an input pattern via simulation of a trained generator model. In an embodiment, the input pattern is a design layout including a hotspot pattern. In an embodiment, the feature pattern 613 corresponds to the hotspot pattern. In an embodiment, the feature pattern and the related input pattern can be stored in a hotspot pattern database.
[0105] In another embodiment, the feature pattern can be further modified, verified and validated as discussed below to ensure that the feature pattern meets the design specifications when subjected to the patterning process. The validation can be based on a simulation of the patterning process using the feature model. The simulated result of the patterning process can be a simulated pattern that can be printed on a substrate. The simulation result can be verified with respect to a design rule check and / or a manufacturability rule check. The following process discusses additional steps of the method.
[0106] In an embodiment, in process P615, the method includes converting the feature pattern into a feature outline representation. The feature outline representation refers to the outline (i.e., the shape or geometric shape) of the pattern within the feature pattern. Converting the feature pattern into the outline representation includes extracting the outline of the features within the feature pattern. The outline can be extracted, for example, based on image processing configured to identify the edges or general shape of the pattern. Once the edges are extracted, the outline can be converted into a geometric shape (e.g., in a GDS format) for further analysis, such as design rule checking.
[0107] In an embodiment, in process P616, before analyzing the contour or geometric shape, pre-processing can be performed on the free-form contour (e.g., curve pattern). For example, pre-processing can involve regularizing the contour representation to "Manhattanize" the free-form contour so that only horizontally and vertically extending segments are obtained in the converted polygon.
[0108] In process P617, analysis of a geometry or feature outline representation (e.g., a Manhattanized polygon) involves applying a design rule check to the feature outline representation. The design rule check may be an algorithm including conditional statements (e.g., if-then conditions) that define whether a feature pattern may be printed within design specifications. For example, the design rule check may be based on geometry and dimensions. In an embodiment, a portion of a feature pattern (or outline) may not satisfy the design rule check. In other words, portions of a feature pattern that may have defects or errors when printed are identified.
[0109] Portions of the pattern that do not satisfy the design rule check may be modified. For example, in process P619, the feature outline representation is modified based on the design rule check to increase the likelihood that the feature pattern can be printed. For example, the modification may involve increasing and / or decreasing the CD of features within the feature pattern. The amount of modification may be a predetermined rule or based on a simulation of the patterning process.
[0110] In an embodiment, optical proximity correction (OPC) may be applied to the feature pattern.For example, process P621 involves determining an optical proximity correction for a modified feature profile via simulation of an optical proximity correction model.
[0111] In addition, the feature pattern modified with OPC can be passed through a simulation process of the patterning process. For example, in process P623, a simulated pattern of the substrate corresponding to the modified feature profile is determined through a simulation of a process model of the patterning process (such as previously discussed). The simulated pattern can be used to verify and validate the modified feature pattern. The verification can be based on a comparison of defect data obtained from a printed substrate corresponding to a pattern similar to the feature pattern. The verification can indicate whether the feature pattern corresponds to a hot spot pattern.
[0112] The above method has multiple applications. For example, the feature pattern obtained above (or the modified feature pattern) can be used to determine the settings of the patterning process based on the feature pattern and / or the modified feature profile via simulation of a process model of the patterning process in process P625. The settings of the patterning process can involve optimization of parameters of the patterning process. In an embodiment, the settings of the patterning process are values of process variables including dose, focus and / or optical parameters.
[0113] The settings determined based on the feature pattern may be further used to print the feature pattern on a substrate via a lithography device in process P627.
[0114] Figure 7 An overview of the training process of a machine learning model based on a generative adversarial network architecture is described. In an embodiment, a generator model 701 receives an input pattern 701a in the form of a pixelated image or vector. In an embodiment, the input pattern 701a is a 100-dimensional vector, each element having a true value between 0 and 1. The generator model 701 is a convolutional neural network with multiple layers, as described. Each layer can have a specific step size and a specific kernel. The last layer of the generator model 701 outputs a feature pattern 705 (also referred to as a false pattern 705). The feature pattern 705 is received by a discriminator model 702 as another CNN. The discriminator model 702 also receives a true pattern 706 (or a set of true patterns) in the form of a pixelated image. Based on the true pattern 706, the discriminator model determines whether the feature pattern is false (e.g., label L1) or true (e.g., label L2), and assigns a label accordingly. The set of true patterns can be a set of fragments of a printed wafer. Therefore, the training of the model 702 is based on multiple true patterns. Therefore, training is based on a batch of real patterns together with a batch of fake generated patterns. Figure 8 The training method is discussed in more detail below.
[0115] In an embodiment, the input pattern 701 may be a seed hotspot image. The seed hotspot image may be obtained from a lithography process simulation with one or more design layouts as input. For example, the simulation may involve an OPC simulation to determine a mask layout via an OPC model and a mask model simulation. In addition, an optical model, a resist model, and a manufacturability check simulation may be performed to obtain a simulated substrate pattern. The simulated pattern may be a hotspot pattern or a non-hotspot pattern that reveals whether a defect may be visualized on a substrate when the OPC corrected design layout is subjected to a patterning process.
[0116] In an embodiment, a plurality of design layouts may be simulated, and locations on the design layouts where hot spots are observed may be selected as seed hot spot images.
[0117] Figure 8It is a flowchart of a method for training a generator model for generating a characteristic pattern of a patterning process discussed above. The following training method is based on a generative adversarial network (GAN), which includes two machine learning models trained together (specifically, relative to each other): a generator model (e.g., CNN) and a discriminator model (e.g., CNN). The generator model can take a random vector (z) as input, and output an image that can be referred to as a false image. A false image is an image of a specific type (e.g., a hotspot pattern) that has never actually existed before. On the other hand, a real image refers to a previously existing image (e.g., a hotspot pattern for a printed substrate), which can be used during training of a generator model and a discriminator model. A real image may also be referred to as a ground truth or training pattern. The training goal is to train a generator model to generate a false image that is closely similar to a real image. For example, the features of a false image match the features of a real image by at least 95%. Therefore, the trained generator model can generate a false image (i.e., a characteristic pattern) of a specific type (e.g., hotspot, non-hotspot, etc.) with a high degree of accuracy.
[0118] In process P801, the training method involves obtaining a machine learning model, which includes a generator model configured to generate a feature pattern and a discriminator model configured to distinguish the feature pattern from the training pattern. During training, the generator model does not know how the training pattern (e.g., hotspot pattern) (i.e., the real pattern) looks. On the other hand, the discriminator model knows the training pattern. Therefore, after completing the training process, the generator model is robust and can generate feature patterns for any type of pattern with high accuracy.
[0119] In an embodiment, the training pattern comprises a hotspot pattern or a set of non-hotspot patterns obtained from a previously printed substrate. In an embodiment, the training pattern may be generated via a simulation of a patterning process model (e.g., as previously discussed), measurement data of a printed substrate, and / or a database storing printed patterns. The training pattern may be associated with a marker such as a hotspot. In an embodiment, the marker may be a non-hotspot, pattern type 1, pattern type 2, a true pattern, etc. Pattern type 1 and pattern type 2 refer to any user defined pattern.
[0120] In an embodiment, the generator model (G) may be a convolutional neural network. The generator model (G) takes a random noise vector z as input and generates an image. In an embodiment, the image may be referred to as a false image or a feature image. The false image may be expressed as X fake =G(z). In an embodiment, the generator model can be augmented with supplementary information such as labels during the training process. Therefore, the trained generator model can generate feature images of specific labels (such as hot spot patterns) as required by the user.
[0121] The generator model (G) can be associated with a first cost function. The first cost function enables tuning of parameters of the generator model so that the cost function is improved (e.g., maximized or minimized). In an embodiment, the first cost function includes a first log-likelihood term that determines the probability that the feature pattern is false given an input vector.
[0122] An example of the first cost function can be expressed by the following Equation 1:
[0123] Ls=E[logP(S=fake|Xfake)]...(1)
[0124] In the above equation 1, the log-likelihood of the conditional probability is calculated. In this equation, S refers to the source assigned as false by the discriminator model, and Xfake is the output of the generator model, i.e., the false image. Therefore, in an embodiment, the training method minimizes the first cost function (L). Therefore, the generator model will generate false images (i.e., feature images) so that the conditional probability that the discriminator model realizes the false image as false is low. In other words, the generator model will gradually generate more and more real images or patterns.
[0125] In another example, the generator model can be configured to generate images based on a specific type. In this case, the first cost function (in equation 1) can include an additional term related to the probability of type c, as shown below:
[0126] Lc=E[logP(C=c|Xfake)]...(2)
[0127] Equation 2 above indicates the log-likelihood that the generator model generates an image of a particular type c. In an embodiment, the label c can be a hotspot pattern or a non-hotspot pattern. In an embodiment, L c It can be maximized, for example, to maximize the probability of generating a hotspot pattern.
[0128] In an embodiment, the discriminator model (D) can be a convolutional neural network. The discriminator model (D) receives real images and false images as input, and outputs the probability that the input is a false image or a real image. The probability can be expressed as P(S|X)=D(X). In other words, if the false image generated by the generator model is not good (i.e., close to the real image), the discriminator model will output a low probability value (e.g., less than 50%) for the input image. This indicates that the input image is a false image. As training progresses, the images generated by the generator model are extremely similar to real images, so that, in the end, the discriminator model may not be able to distinguish whether the input image is a false image or a real image.
[0129] In an embodiment, the discriminator model may be associated with a second cost function. The second cost function enables tuning of the parameters of the discriminator model so that the cost function is improved (e.g., maximized). In an embodiment, the second cost function includes a second log-likelihood term that determines the conditional probability that the false pattern (i.e., the characteristic pattern) is real given the training pattern. The probabilistic comparison between the false pattern and the training pattern allows the discriminator model to gradually become better at identifying false images from real images.
[0130] An example of the second cost function can be expressed by the following Equation 3:
[0131] LsE[logP(Sreal|Xreal)]+Elog(Sfake|Xfake)](3)
[0132] In the above equation, the log-likelihood of the conditional probability is calculated. In the formula, S refers to the input of the real image Xrea l In the case of , the input image is assigned as a real source, and in the case of the input image is a fake image Xfake (i.e., a fake image of the generator model), it is assigned as a fake source. In an embodiment, the training method maximizes the second cost function (Equation 3). Therefore, the discriminator model gradually becomes better at distinguishing real images from fake images.
[0133] In another example, the discriminator model can be configured to assign labels to images based on a specific type. In this case, the second cost function (in equation 3) can include an additional term related to the probability of type c, as shown below:
[0134] Lc=E[logP(C=c|Xreal)]+E[logP(C=c|Xfake)]..(4)
[0135] Equation 4 above indicates the log-likelihood that the discriminator model assigns an image of a specific type c (eg, hotspot or non-hotspot).
[0136] Thus, the generator model is trained simultaneously with the discriminator model, such that the discriminator model provides feedback to the generator model on the quality of the fake images (i.e., how closely the fake images resemble real images). Additionally, as the quality of the fake images gets better, the discriminator model needs to get better at distinguishing fake images from real images. The goal is to train the models until they no longer improve each other. For example, the improvement may be indicated by the value of the corresponding cost function not substantially changing upon further iterations.
[0137] In addition, process P803 involves training the generator model and the discriminator model in a collaborative manner (e.g., in series) based on a training set including training patterns, so that the generator model generates a feature pattern that matches the training pattern, and the discriminator model recognizes the feature pattern as the training pattern. In other words, the generator model is trained collaboratively with the discriminator model, and vice versa, so that the output of one model improves the prediction of the other model or the model.
[0138] Training is an iterative process, wherein the iterations include: generating a feature pattern via simulation of a generator model with an input vector, and evaluating a first cost function (e.g., Equation 1 or Equation 2 discussed above). In an embodiment, the input vector may be an n-dimensional random vector (e.g., a 100-dimensional vector, a 100×100-dimensional vector), wherein each element of the vector is a randomly assigned value. For example, each element of the input vector may have a specific value or a random value between 0 and 1, such as representing a probability value. For example, the input vector may be [0, 0.01, 0.05, 0.5, 0.6, 0.02…]. In an embodiment, the random value may be randomly selected from a Gaussian probability distribution.
[0139] In an embodiment, the input vector may be a seed hotspot image. The seed hotspot image may be obtained from a simulation of a lithography process with one or more design layouts as input, as previously discussed with respect to process P611.
[0140] In an embodiment, the generator model generates a feature pattern including features similar to the training pattern. In an embodiment, the feature pattern and the training pattern may include a non-hotspot pattern and / or a user-defined pattern.
[0141] Additionally, in an iteration within process P803, the feature pattern is received by the discriminator model to distinguish the feature pattern from a corresponding true pattern or training pattern and evaluate a second cost function. The discriminator model knows the true pattern because it is one of the inputs to the discriminator model for training purposes.
[0142] In an embodiment, the differentiation involves determining the probability that the characteristic pattern is a training pattern. For example, using equation 3 or 4, where a true pattern is given and a false pattern is received as a characteristic pattern from a generator model. In response to the probability value, a label is assigned to the characteristic pattern. The label indicates whether the characteristic pattern is a true pattern or a false pattern.
[0143] In an embodiment, in response to the probability exceeding a threshold (eg, greater than 90%), the characteristic pattern is marked as a true pattern.
[0144] Additionally, training involves adjusting parameters of the generator model to improve a first cost function, and adjusting parameters of the discriminator model to improve a second cost function. In an embodiment, adjusting the parameters may be based on a technique involving backpropagation through various layers of the machine learning model to update the model parameters. In an embodiment, the gradient of the cost function may be calculated during backpropagation, and the weights and biases of different layers may be adjusted based on the gradient to, for example, reduce (or minimize) the cost function.
[0145] In an embodiment, the first cost function may be reduced (or minimized) so that the false images generated by the generator model closely resemble the real images, as previously discussed with respect to Equations 1 and 2. Similarly, the second cost function may be increased (or maximized) so that the discriminator model can better distinguish false images from real images, as previously discussed with respect to Equations 1 and 2.
[0146] After multiple iterations of the training process, the generator model and the discriminator model converge. In other words, adjustment of the parameters of the corresponding model does not improve the corresponding cost function. Therefore, the generator model is regarded as a trained generator model 810 (an example of a trained generator model 601). Now, the trained generator model 810 can be used to directly determine the characteristic pattern based on, for example, a seeding hotspot image corresponding to the design layout. Effectively, a design pattern including a hotspot pattern and / or a user-defined pattern is generated via simulation of the trained generator model.
[0147] Fig. 9A is an example of a real pattern 901, and Fig. 9B 902 is an example of a feature pattern 902 generated by a trained generator model (e.g., 603 or 910). Feature pattern 902 includes features that are substantially similar to features of real pattern 901. Therefore, the trained generator model (e.g., 603 or 910) generates a pattern that can match the real pattern. In an embodiment, multiple features in the feature pattern may not completely match corresponding features in the real pattern (e.g., in shape, size, location, orientation, etc.).
[0148] Fig.10 Exemplary deficiencies and exemplary ways to overcome them are described. Fig.10As shown in , for certain settings of process variables such as dose / focus, footing 2402 and necking 2412 type failures can be observed. In the case of footing, de-scumming can be performed to remove the footing 2404 at the substrate. In the case of necking 2412, the resist thickness can be reduced by removing the top layer 2414. Therefore, the defect-based process window can be improved at the expense of the resist. In an embodiment, modeling / simulations can be performed to determine the optimal thickness without changing / compromising the process window (i.e., with a desired yield), so fewer defects (such as necking / footing) can be observed.
[0149] According to an embodiment, a method for generating a feature pattern for a patterning process is provided. The method includes: obtaining a trained generator model and an input pattern, the trained generator model being configured to generate a feature pattern; and generating the feature pattern based on the input pattern via simulation of the trained generator model, wherein the input pattern is at least one of a random vector or a pattern type.
[0150] In an embodiment, the pattern of features is a patterning device pattern to be printed on a substrate subjected to the patterning process.
[0151] In an embodiment, the input pattern is obtained via simulation of a process model of a patterning process with a design layout as input resulting in a hotspot pattern.
[0152] In an embodiment, the process model includes an optical proximity correction model and a lithography manufacturability check model.
[0153] In an embodiment, the method further comprises: converting the feature pattern to a feature outline representation; applying a design rule check to the feature outline representation; and modifying the feature outline representation based on the design rule check to increase the likelihood that the feature pattern can be printed.
[0154] In an embodiment, converting the feature pattern comprises: extracting contours of features within the feature pattern; and converting the contours into geometric shapes and / or Manhattanizing the feature pattern.
[0155] In an embodiment, the method further comprises: determining an optical proximity correction for a modified feature profile via simulation of the optical proximity correction model; and determining a simulated pattern of the substrate corresponding to the modified feature profile via simulation of the process model of the patterning process.
[0156] In an embodiment, the method further comprises determining settings for the patterning process based on the feature pattern and / or the modified feature profile via simulation of the process model of the patterning process.
[0157] In an embodiment, said settings of the patterning process are values of process variables including dose, focus and / or optical parameters.
[0158] In an embodiment, the method further comprises: applying the setting of the patterning process via the lithography equipment to print the feature pattern on the substrate.
[0159] In an embodiment, the trained generator model is a convolutional neural network.
[0160] In an embodiment, the trained generator model is trained according to a machine learning training method known as a generative adversarial network.
[0161] In an embodiment, said characteristic pattern and said input pattern are pixelated images.
[0162] In an embodiment, the input pattern comprises a design layout including a hotspot pattern.
[0163] In addition, the present disclosure provides a method for training a machine learning model for generating a feature pattern of a patterning process. The method includes: obtaining a machine learning model, the machine learning model including: (i) a generator model configured to generate a feature pattern to be printed on a substrate subjected to a patterning process, and (ii) a discriminator model configured to distinguish the feature pattern from a training pattern; and training the generator model and the discriminator model in a mutually cooperative manner based on a training set including the training pattern via a computer hardware system, so that the generator model generates the feature pattern matching the training pattern, and the discriminator model identifies the feature pattern as the training pattern, wherein the feature pattern and the training pattern include a hotspot pattern.
[0164] In an embodiment, training is an iterative process, the iterations comprising: generating the feature pattern via simulation of the generator model using an input vector; evaluating a first cost function associated with the generator model; distinguishing the feature pattern from the training pattern via the discriminator model; evaluating a second cost function associated with the discriminator model; and adjusting parameters of the generator model to improve the first cost function, and adjusting parameters of the discriminator model to improve the second cost function.
[0165] In an embodiment, the input vector is a random vector and / or a seed hotspot image.
[0166] In an embodiment, the seed hotspot image is obtained from a simulation of a lithography process with a design layout as input.
[0167] In an embodiment, distinguishing comprises: determining a probability that the characteristic pattern is the training pattern; and assigning a label to the characteristic pattern in response to the probability, the label indicating whether the characteristic pattern is a real pattern or a false pattern.
[0168] In an embodiment, in response to the probability exceeding a threshold, the characteristic pattern is marked as a true pattern.
[0169] In an embodiment, the first cost function comprises a first log-likelihood term which determines the probability that the characteristic pattern is false given the input vector.
[0170] In an embodiment, the parameters of the generator model are adjusted so that the first log-likelihood term is minimized.
[0171] In an embodiment, the second cost function comprises a second log-likelihood term which determines the probability that the characteristic pattern is real given the training patterns.
[0172] In an embodiment, the second model parameters are adjusted so as to maximize the second log-likelihood term.
[0173] In an embodiment, the training pattern comprises a hotspot pattern.
[0174] In an embodiment, the training patterns are obtained from simulations of a process model of the patterning process, metrology data of printed substrates and / or a database storing printed patterns.
[0175] In an embodiment, the characteristic pattern comprises features similar to the training pattern.
[0176] In an embodiment, the characteristic pattern and the training pattern further include a non-hotspot pattern and / or a user-defined pattern.
[0177] In an embodiment, the method further comprises generating, via simulation of the trained generator model, a design pattern comprising hotspot patterns and / or user-defined patterns.
[0178] In an embodiment, the generator model and the discriminator model are convolutional neural networks.
[0179] Fig.111 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, which is 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.
[0180] The computer system 100 can be coupled to a display 112, such as a cathode ray tube (CRT) or a flat panel display or a touch panel display, via the bus 102 for displaying information to a computer user. An input device 114 including alphanumeric keys and other keys is coupled 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 directional information and command selections to the processor 104, and for controlling cursor movement on the display 112. The input device typically has two degrees of freedom in 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.
[0181] According to one embodiment, some parts 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 processing 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 in place of or in combination with software instructions. Therefore, the description herein is not limited to any specific combination of hardware circuitry and software.
[0182] As used herein, the term "computer-readable medium" refers to any medium that participates in providing instructions to the processor 104 for execution. Such media can be in many forms, including but not limited to non-volatile media, volatile media, and transmission media. Non-volatile media include, for example, optical disks or disks, such as storage devices 110. Volatile media include volatile memories, such as main memory 106. Transmission media include coaxial cables, copper wires, and optical fibers, including lines containing bus 102. Transmission media can also be in 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, RAMs, PROMs and EPROMs, FLASH-EPROMs, any other memory chips or cartridges, carriers as described below, or any other media that can be read by a computer.
[0183] Various forms of computer-readable media may be involved in carrying one or more sequences of one or more instructions to the processor 104 for execution. For example, initially the instructions may be carried on a disk of a remote computer. The remote computer may load the instructions into its volatile memory and send the instructions via a telephone line using a modem. The modem at the local end of the computer system 100 may receive the data of the telephone line and use an infrared transmitter to convert the data into an infrared signal. An infrared detector coupled to the bus 102 may receive the data carried in the infrared signal and place the data on the bus 102. The bus 102 carries the data to the main memory 106, from which the processor 104 retrieves and executes the instructions. The instructions received by the main memory 106 may optionally be stored on the storage device 110 before or after being executed by the processor 104.
[0184] 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 coupling 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. Wireless connections 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.
[0185] 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 packet data 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 are exemplary forms of carrier waves that transport the information, carrying the digital data to and from the computer system 100.
[0186] The computer system 100 can send messages and receive data (including code) via the network, network link 120, and communication interface 118. In the example of the Internet, server 130 can transmit the requested code for an 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 methods described herein. The received code can be executed by processor 104 as 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.
[0187] Fig.12 An exemplary lithographic projection apparatus that may incorporate the techniques described herein is schematically depicted. The apparatus comprises:
[0188] - an illumination system IL for conditioning the radiation beam B. In this particular case, the illumination system also comprises a radiation source SO;
[0189] a first object table (e.g. patterning device table) 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 with respect to the item PS;
[0190] a second object table (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;
[0191] - 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).
[0192] As depicted herein, the device is of the transmissive type (i.e., with a transmissive patterning device). However, in general, it can also be of the reflective type, for example (with a reflective patterning device). The device can use different kinds of patterning devices than classical masks; examples include programmable mirror arrays or LCD matrices.
[0193] A source SO (e.g. a mercury lamp or an excimer laser, a laser produced plasma (LPP) EUV source) generates a radiation beam. This beam is fed into an illumination system (illuminator) IL, for example directly or after having passed through an adjustment member such as a beam expander Ex. The illuminator IL may include adjustment members AD for setting the outer radial extent and / or the inner radial extent (commonly referred to as σ outer and σ inner, respectively) of the intensity distribution in the beam. In addition, the illuminator IL will typically include various other components, such as an integrator IN and a condenser CO. In this way, the beam B impinging on the pattern forming device MA has a desired uniformity and intensity distribution in its cross section.
[0194] about Fig.12 It should be noted that the source SO can be within the housing of the lithographic projection device (this is often the case when the source SO is, for example, a mercury lamp), but it can also be remote from the lithographic projection device, the radiation beam it generates being guided into the device (for example with the aid of appropriate guiding mirrors); the latter case is often the case when the source SO is an excimer laser (for example based on KrF, ArF or F2 laser action).
[0195] The beam PB then intercepts the patterning device MA which is held on the patterning device table MT. After passing the patterning device MA, the beam B passes through a lens PL 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 different target portions C are positioned in the path of the beam PB. 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 acquisition of the patterning device MA from a patterning device library or during scanning. In general, the patterning device MA will be accurately positioned with the aid of the interferometry means not in the patterning device library. Fig.12 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. 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.
[0196] The depicted tools can be used in two different modes:
[0197] - in step mode, the patterning device table MT is held substantially stationary and the entire patterning device image is projected once (i.e. a single “flash”) 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 illuminated by the beam PB;
[0198] - In scan mode, essentially the same situation applies, except that a given target portion C is not exposed in a single "flash". Alternatively, 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 across the patterning device image; while the substrate table WT is simultaneously moved in the same or opposite direction at a speed V=Mv, where M is the magnification of the lens PL (typically M=1 / 4 or 1 / 5). In this way, a relatively large target portion C can be exposed without having to compromise resolution.
[0199] Fig.13 Another exemplary lithographic projection apparatus 1000 that may be utilized in conjunction with the techniques described herein is schematically depicted.
[0200] The lithography projection apparatus 1000 comprises:
[0201] - Source collector module SO;
[0202] - an illumination system (illuminator) IL configured to condition a radiation beam B (e.g. EUV radiation);
[0203] a support structure (e.g. patterning device table) MT configured to support a patterning device (e.g. mask or reticle) MA and connected to a first positioner PM configured to accurately position the patterning device;
[0204] a substrate table (e.g. wafer stage) WT configured to hold a substrate (e.g. a resist-coated wafer) W and connected to a second positioner PW configured to accurately position the substrate; and
[0205] - a projection system (eg a reflective projection system) PS configured to project a pattern imparted to the radiation beam B via the patterning device MA onto a target portion C of the substrate W (eg comprising one or more dies).
[0206] As depicted here, the apparatus 1000 is of the reflective type (e.g., using a reflective patterning device). It should be noted that since most materials are absorptive in the EUV wavelength range, the patterning device can have a multilayer reflector including, for example, multiple stacks of 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. Since most materials are absorptive at EUV and X-ray wavelengths, a thin piece of patterned absorbing material on the patterning device topology (e.g., a TaN absorber on top of a multilayer reflector) defines where features will be printed (positive resist) or not printed (negative resist).
[0207] refer to Fig.13 , 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 into a plasma state having at least one element having one or more emission lines in the EUV range, such as xenon, lithium, or tin. In one such method, often referred to as laser produced plasma ("LPP"), a plasma may be generated by irradiating a fuel, such as a droplet, stream, or cluster of a material having a line emitting element, with a laser beam. The source collector module SO may be a laser ( Fig.13 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.
[0208] In these 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, appropriate 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.
[0209] The illuminator IL may include an adjuster for adjusting the angular intensity distribution of the radiation beam. In general, at least the outer radial extent and / or the inner radial extent (commonly referred to as σ outer and σ inner, 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 arrangement and a faceted pupil mirror arrangement. The illuminator may be used to adjust the radiation beam to have a desired uniformity and intensity distribution in its cross-section.
[0210] The radiation beam B is incident on a patterning device (e.g. a mask) MA, which is 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 radiation beam B 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 interferometric device, a linear encoder or a capacitive sensor), the substrate table WT can be precisely moved, for example in order to position a different target portion C 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.
[0211] The depicted device 1000 may be used in at least one of the following modes:
[0212] 1. In step mode, the support structure (e.g. patterning device table) MT and the substrate table WT are kept substantially stationary (i.e. a 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.
[0213] 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.
[0214] 3. In another mode, the support structure (e.g. patterning device table) MT remains substantially fixed to hold the programmable patterning device, and the substrate table WT is moved or scanned while projecting a pattern imparted to the radiation beam onto a target portion C. In this mode, typically a pulsed radiation source is 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 can be readily applied to maskless lithography using a programmable patterning device, such as a programmable mirror array of the type mentioned above.
[0215] Fig.14The 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), wherein an extremely hot plasma 210 is generated to emit radiation in the EUV range of the electromagnetic spectrum. For example, an extremely hot plasma 210 is generated by a discharge that causes at least a 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 tin (Sn) plasma is provided to generate EUV radiation.
[0216] The radiation emitted by the hot plasma 210 is transferred from the source chamber 211 to the collector chamber 212 via an optionally selected 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.
[0217] The collector chamber 211 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 passing through the collector CO may be reflected from the grating spectral filter 240 to be focused in 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 so 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.
[0218] The radiation then passes through an illumination system IL which may include a faceted field mirror arrangement 22 and a faceted pupil mirror arrangement 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. After reflection of the radiation beam 21 at the patterning device MA held by the support structure MT, a patterned beam 26 is formed and is imaged by the projection system PS via reflective elements 28, 30 onto a substrate W held by a substrate table WT.
[0219] 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.14 The reflective elements shown have from 1 to 6 additional reflective elements.
[0220] like Fig.14 The illustrated collector optic CO is depicted as a nested collector with grazing incidence reflectors 253, 254 and 255, merely as 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 optic CO can be used in combination with a discharge generated plasma source, often referred to as a DPP source.
[0221] Alternatively, the source collector module SO may be as follows Fig.15 Components of the LPP radiation system shown in . The laser LA is configured to deposit laser energy into a fuel such as xenon (Xe), tin (Sn), or lithium (Li), thereby generating a highly ionized plasma 210 with an electron temperature of tens of electron volts. The high-energy radiation generated during the deexcitation and recombination of these ions is emitted from the plasma, collected by the near normal incidence collector optical element CO, and focused onto an opening 221 in the enclosure structure 220.
[0222] The embodiments may be further described using the following terms:
[0223] 1. A method for generating a feature pattern for a patterning process, the method comprising:
[0224] Obtaining a trained generator model and an input pattern, wherein the trained generator model is configured to generate a feature pattern; and
[0225] The feature pattern is generated based on the input pattern via simulation of the trained generator model, wherein the input pattern is at least one of a random vector or a type of pattern.
[0226] 2. A method as described in clause 1, wherein the feature pattern is a pattern forming device pattern to be printed on a substrate undergoing the patterning process.
[0227] 3. The method of any of clauses 1 to 2, wherein the input pattern is obtained via simulation of a process model of the patterning process with a design layout as input resulting in a hotspot pattern.
[0228] 4. The method of clause 3, wherein the process model comprises an optical proximity correction model and a lithography manufacturability check model.
[0229] 5. The method of any one of clauses 1 to 4, further comprising:
[0230] converting the feature pattern into a feature contour representation;
[0231] applying a design rule check to the feature outline representation; and
[0232] The feature outline representation is modified based on the design rule check to increase the likelihood that the feature pattern can be printed.
[0233] 6. The method of clause 5, wherein said converting said characteristic pattern comprises:
[0234] extracting the contours of the features within the feature pattern; and
[0235] The contours are converted into geometric shapes and / or the characteristic patterns are Manhattanized.
[0236] 7. The method of any one of clauses 4 to 6, further comprising:
[0237] determining an optical proximity correction for a modified feature profile via simulation of the optical proximity correction model;
[0238] A simulated pattern of the substrate corresponding to the modified feature profile is determined via simulation of the process model of the patterning process.
[0239] 8. The method of any one of clauses 1 to 7, further comprising:
[0240] Via simulation of the process model of the patterning process, settings for the patterning process are determined based on the feature pattern and / or the modified feature profile.
[0241] 9. The method of clause 8, wherein the settings of the patterning process are values of process variables including dose, focus and / or optical parameters.
[0242] 10. The method of any one of clauses 8 to 9, further comprising:
[0243] The feature pattern is printed on the substrate via the lithography equipment using the settings of the patterning process.
[0244] 11. A method as described in any of clauses 1 to 10, wherein the trained generator model is a convolutional neural network.
[0245] 12. A method as described in any of clauses 1 to 11, wherein the trained generator model is trained according to a machine learning training method known as a generative adversarial network.
[0246] 13. A method as described in any of clauses 1 to 12, wherein the characteristic pattern and the input pattern are pixelated images.
[0247] 14. The method of any of clauses 1 to 3, wherein the input pattern comprises a design layout comprising a hotspot pattern.
[0248] 15. A method for training a machine learning model for generating a characteristic pattern of a patterning process, the method comprising:
[0249] obtaining a machine learning model comprising: (i) a generator model configured to generate a feature pattern to be printed on a substrate undergoing a patterning process, and (ii) a discriminator model configured to distinguish the feature pattern from a training pattern; and
[0250] training the generator model and the discriminator model in a mutually cooperative manner based on a training set including the training pattern via a computer hardware system, so that the generator model generates the feature pattern matching the training pattern and the discriminator model recognizes the feature pattern as the training pattern,
[0251] Wherein, the characteristic pattern and the training pattern include hotspot patterns.
[0252] 16. The method of clause 15, wherein the training is an iterative process, the iterations comprising:
[0253] generating the characteristic pattern via simulation of the generator model using an input vector;
[0254] evaluating a first cost function associated with the generator model;
[0255] distinguishing the characteristic pattern from the training pattern via the discriminator model;
[0256] evaluating a second cost function associated with the discriminator model; and
[0257] Parameters of the generator model are adjusted to improve the first cost function, and parameters of the discriminator model are adjusted to improve the second cost function.
[0258] 17. A method as described in any of clauses 15 to 16, wherein the input vector is a random vector and / or a seed hotspot image.
[0259] 18. The method of clause 17, wherein the seed hotspot image is obtained from a simulation of a lithography process having a design layout as input.
[0260] 19. The method of any one of clauses 16 to 18, wherein the distinguishing comprises:
[0261] determining a probability that the characteristic pattern is the training pattern; and
[0262] Responsive to the probability, a label is assigned to the characteristic pattern, the label indicating whether the characteristic pattern is a real pattern or a false pattern.
[0263] 20. The method of clause 19, wherein, in response to the probability exceeding a threshold, the characteristic pattern is marked as a true pattern.
[0264] 21. A method as described in any of clauses 16 to 20, wherein the first cost function includes a first log-likelihood term that determines the probability that the characteristic pattern is false given the input vector.
[0265] 22. A method as described in item 21, wherein the parameters of the generator model are adjusted so that the first log-likelihood term is minimized.
[0266] 23. A method as described in any of clauses 16 to 22, wherein the second cost function includes a second log-likelihood term that determines the probability that the characteristic pattern is real given the training pattern.
[0267] 24. The method of clause 23, wherein the second model parameters are adjusted so that the second log-likelihood term is maximized.
[0268] 25. The method of any one of clauses 15 to 23, wherein the training pattern comprises a hotspot pattern.
[0269] 26. The method of any of clauses 15 to 25, the training pattern being obtained from a simulation of a process model of the patterning process, metrology data of printed substrates and / or a database storing printed patterns.
[0270] 27. The method of any one of clauses 15 to 26, wherein the characteristic pattern comprises features similar to the training pattern.
[0271] 28. The method of any one of clauses 15 to 27, wherein the characteristic pattern and the training pattern further comprise non-hotspot patterns and / or user-defined patterns.
[0272] 29. The method of any of clauses 15 to 28, further comprising generating, via simulation of the trained generator model, a design pattern comprising hotspot patterns and / or user-defined patterns.
[0273] 30. A method as described in any of clauses 14 to 29, wherein the generator model and the discriminator model are convolutional neural networks.
[0274] The concepts disclosed herein can simulate or mathematically model any general imaging system for imaging sub-wavelength features, and can be used in particular with emerging imaging technologies that can produce shorter and shorter wavelengths. Emerging technologies already in use include extreme ultraviolet (EUV), DUV lithography that can produce 193nm wavelengths by using ArF lasers and even 157nm wavelengths by using fluorine lasers. In addition, EUV lithography can produce wavelengths in the range of 20nm to 5nm by using a synchrotron or by using high energy electrons to impinge on a material (solid or plasma) so as to produce photons in this range.
[0275] 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, for example, a lithography imaging system for imaging on substrates other than silicon wafers.
[0276] 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 generating a feature pattern for a patterning process, the method comprising: Obtaining a trained generator model and an input pattern, wherein the trained generator model is configured to generate a feature pattern; as well as The feature pattern is generated based on the input pattern via simulation of the trained generator model, wherein the input pattern is at least one of a random vector or a type of pattern.
2. The method according to claim 1, wherein: The feature pattern is the patterning device pattern to be printed on the substrate subjected to the patterning process.
3. The method according to any one of claims 1 to 2, wherein: The input pattern is obtained via simulation of a process model of the patterning process with a design layout as input resulting in a hotspot pattern.
4. The method according to claim 3, wherein: The process model includes an optical proximity correction model and a lithography manufacturability check model.
5. The method according to any one of claims 1 to 4, further comprising: converting the feature pattern into a feature contour representation; applying a design rule check to the feature outline representation; as well as The feature outline representation is modified based on the design rule check to increase the likelihood that the feature pattern can be printed.
6. The method according to claim 5, wherein: The converting the characteristic pattern comprises: extracting the contours of the features within the feature pattern; and The contours are converted into geometric shapes and / or the characteristic patterns are Manhattanized.
7. The method according to any one of claims 4 to 6, further comprising: determining an optical proximity correction for a modified feature profile via simulation of the optical proximity correction model; A simulated pattern of the substrate corresponding to the modified feature profile is determined via simulation of the process model of the patterning process.
8. The method according to any one of claims 1 to 7, further comprising: Via simulation of the process model of the patterning process, settings for the patterning process are determined based on the feature pattern and / or the modified feature profile.
9. The method according to claim 8, wherein: The settings of the patterning process are values of process variables including dose, focus and / or optical parameters.
10. The method according to any one of claims 8 to 9, further comprising: The feature pattern is printed on the substrate via the lithography equipment using the settings of the patterning process.
11. The method according to any one of claims 1 to 10, wherein: The trained generator model is a convolutional neural network.
12. The method according to any one of claims 1 to 11, wherein: The trained generator model is trained according to a machine learning training method known as a generative adversarial network.
13. The method according to any one of claims 1 to 12, wherein: The characteristic pattern and the input pattern are pixelated images.
14. The method according to any one of claims 1 to 3, wherein: The input pattern includes a design layout including a hotspot pattern.
