Apparatus and method for generating a blur removal model and removing blur from an image.

Abstract

This specification describes a method and system for removing blur from an image of a patterned substrate by training the deblurring model using a deblurring model and depth data associated with multiple layers of the patterned substrate. [Solution] The method involves obtaining a simulated image of a substrate via a simulator that uses a target pattern as input, wherein the target pattern includes a first target feature formed on a first layer and a second target feature formed on a second layer located below the first layer; determining edge range data for the substrate features based on depth data associated with multiple layers of the substrate; and adjusting the parameters of a basic model using the simulated image and edge range data associated with the target pattern as training data to generate a deblurring model for a deblurred image of the captured image.

Description

[Technical Field]

[0001] Cross-reference of related applications

[0001] This application claims priority to U.S. Patent Application No. 63 / 091126, filed on 13 October 2020, which is incorporated herein by reference in its entirety.

[0002]

[0002] The description herein relates in general to the processing of images acquired by inspection tools or metrology tools, and more specifically to the deblurring of images using machine learning. [Background technology]

[0003]

[0003] Lithography projection equipment can be used, for example, in the manufacture of integrated circuits (ICs). In such cases, a patterning device (e.g., a mask) can contain or provide patterns ("design layouts") corresponding to individual layers of the IC, and these patterns can be transferred onto target portions (e.g., including one or more dies) on a substrate (e.g., a silicon wafer) coated with a layer of radiation-sensitive material ("resist") by methods such as irradiating target portions through the pattern on the patterning device. Generally, a single substrate contains multiple adjacent target portions (one target portion at a time) onto which patterns are successively transferred by the lithography projection equipment. In some types of lithography projection equipment, the pattern on the entire patterning device is transferred onto one target portion at a time, and such equipment is generally called a stepper. In alternative equipment, generally called a step-and-scan device, the projection beam moves the substrate parallel or antiparallel to a given reference direction ("scan" direction) in synchronization with scanning the patterning device in this reference direction. Different parts of a pattern on a patterning device are progressively transferred to a single target area. Generally, since the lithography projection apparatus has a reduction ratio M (e.g., 4), the speed F at which the substrate is moved is the speed at which the projection beam scans the patterning device × 1 / M. Further information regarding lithography devices such as those described herein can be found, for example, in U.S. Patent No. 6,046,792, incorporated herein by reference.

[0004]

[0004] Before transferring the pattern from the patterning device to the substrate, the substrate may undergo various procedures such as priming, resist coating, and soft baking. After exposure, the substrate may undergo other procedures such as post-bake (PEB), development, hard baking, and measurement / inspection of the transferred pattern ("post-exposure procedures"). These numerous procedures are used as a basis for creating the individual layers of a device, such as an IC. The substrate may then undergo various processes such as etching, ion implantation (doping), metallization, oxidation, and chemical mechanical polishing (all intended to finish the individual layers of the device). If several layers are required for the device, the entire procedure or variations thereof are repeated for each layer. Finally, the device is present in each target portion on the substrate. These devices are then separated from each other by techniques such as dicing or sawing, so that the individual devices can be mounted on a carrier, connected to pins, etc.

[0005]

[0005] Accordingly, manufactured devices such as semiconductor devices generally involve processing a substrate (e.g., a semiconductor wafer) using a number of fabrication processes to form various features and multiple layers of the device. Such layers and features are generally manufactured and processed using, for example, deposition, lithography, etching, chemical mechanical polishing, and ion implantation. Multiple devices may be fabricated on multiple dies on a substrate and then separated into individual devices. This device manufacturing process can be considered a patterning process. The patterning process includes a patterning step such as optical and / or nanoimprint lithography using a patterning device in a lithography apparatus to transfer a pattern on the patterning device to a substrate, and generally (but optionally) includes one or more related pattern processing steps such as resist development with a developing apparatus, baking of the substrate with a baking tool, and etching using the pattern with an etching apparatus. [Overview of the Initiative]

[0006]

[0006] According to one embodiment, a method is provided for training an image deblurring model for processing an image. The method includes obtaining a simulated image of a substrate corresponding to a target pattern via a simulator that uses a target pattern from which a pattern on the substrate is derived. The target pattern includes a first target feature formed on a first layer on the substrate and a second target feature formed on a second layer on the substrate, the second layer being located below the first layer on the substrate. The method further includes determining edge range data for features on the substrate corresponding to the first and second target features of the target pattern based on depth data associated with a plurality of layers of the substrate. The depth data characterizes the blurring of the edges of the features on the substrate as a function of the depth of each feature from the top layer of the substrate. The method further includes using the simulated image of the substrate and the edge range data as training data to adjust the parameters of a basic model and generate a deblurring model. The deblurring model is configured to generate a deblurred image of a captured image of a patterned substrate using edge range data associated with a captured image.

[0007]

[0007] In one embodiment, a method is provided for removing blur from a captured image of a patterned substrate. The method includes identifying features in the captured image based on target patterns and depth data associated with each layer of the patterned substrate, and removing blur from the captured image by removing the blur of each of the features based on the target patterns and depth data.

[0008]

[0008] In one embodiment, a method is provided for removing blur from a captured image of a patterned substrate. The method includes inputting a captured image of the patterned substrate associated with a target pattern and edge range data into a deblurring model.

[0009]

[0009] In one embodiment, a system is provided comprising an electron beam optical system configured to capture an image of a patterned substrate, and one or more processors configured to remove blur from the captured image. The system comprises one or more processors configured to remove blur from the captured image by inputting the captured image and edge range data of the patterned substrate associated with a target pattern into a deblurring model, the deblurring model being trained on edge range data associated with features of the target pattern at a certain depth, and running the deblurring model.

[0010]

[0010] In one embodiment, one or more non-temporary computer-readable media are provided that contain instructions corresponding to the process of the method described herein. In one embodiment, one or more non-temporary computer-readable media are for storing a deblurring model. In one embodiment, one or more non-temporary computer-readable media are configured to generate a deblurred image by the stored deblurring model. In particular, one or more non-temporary computer-readable media store instructions that, when executed by one or more processors, provide a deblurring model. In one embodiment, the deblurring model is generated by the process of the method described herein. For example, the process for generating a deblurring model includes: obtaining a simulated image of a substrate corresponding to a target pattern via a simulator that uses a target pattern from which a pattern on the substrate is derived; determining edge range data for features on the substrate corresponding to a first target feature and a second target feature of the target pattern based on depth data associated with multiple layers of the substrate; and using the simulated image of the substrate and the edge range data as training data to adjust the parameters of a basic model and generate a deblurring model. The deblurring model is configured to generate a deblurred image of the captured image of a patterned substrate using edge range data associated with the captured image.

[0011]

[0011] According to embodiments of the present disclosure, the deblurring model is trained using simulated images converted from a design pattern through a simulator (e.g., a Monte Carlo-based simulator) and depth data associated with the design pattern. The training data, including the simulated images and depth data, can collectively cover significantly and sufficiently more patterns than the images captured by the SEM. The improved pattern coverage can, advantageously, greatly improve the effectiveness and accuracy of the deblurring model. The need for retraining can be greatly reduced or even eliminated.

[0012]

[0012] The above embodiments and other embodiments and features will become apparent to those skilled in the art by examining the following descriptions of specific embodiments in conjunction with the attached drawings. [Brief explanation of the drawing]

[0013] [Figure 1]

[0013] A block diagram of various subsystems of a lithography system according to one embodiment is shown. [Figure 2A]

[0014] This is an image display of a target pattern including multiple features (e.g., contact holes) according to one embodiment. [Figure 2B]

[0015] This is a blurred image of a patterned substrate, according to one embodiment, in which the target pattern (Figure 2A) is printed on a first layer of the patterned substrate. [Figure 2C]

[0015] This is a blurred image of a patterned substrate according to one embodiment, in which the target pattern (Figure 2A) is printed on a second layer of the patterned substrate. [Figure 2D]

[0015] This is a blurred image of a patterned substrate according to one embodiment, in which the target pattern (Figure 2A) is printed on a third layer of the patterned substrate. [Figure 2E]The defocused image of a patterned substrate according to one embodiment, in which the target pattern (of FIG. 2A) is printed on the fourth layer of the patterned substrate. [Figure 2F]

[0016] The defocused image of a patterned substrate according to one embodiment, in which the target pattern (the dotted circle corresponding to FIG. 2A) is superimposed on the image and the defocused layer is the fourth layer of the substrate. [Figure 3]

[0017] A flowchart of a method for training a defocus removal model according to one embodiment. [Figure 4]

[0018] A flowchart of a method for removing defocus from a captured image of a patterned substrate according to one embodiment. [Figure 5]

[0019] A flowchart of another method for removing defocus from a captured image of a patterned substrate according to one embodiment. [Figure 6]

[0020] A flowchart of yet another method for removing defocus from a captured image of a patterned substrate according to one embodiment. [Figure 7]

[0021] Shows the generation of a simulated image from a target pattern according to one embodiment. [Figure 8A]

[0022] A two-dimensional image representation of a target pattern patterned on multiple layers, in which different target features are associated with each layer, according to one embodiment. [Figure 8B]

[0023] A two-dimensional image representation of edge range data determined based on depth data corresponding to each feature of the target pattern (of FIG. 8A), according to one embodiment. [Figure 9]

[0024] Shows the generation of a noisy simulated image according to an embodiment. [Figure 10]

[0025] An image representation of the structure of a defocus removal model configured according to the training in FIG. 3, according to one embodiment. [Figure 11]

[0026] This example demonstrates how to generate a de-blurred image of a simulated image via a de-blurring model that uses depth data as input, according to one embodiment. [Figure 12]

[0027] This example demonstrates how to remove blur from a captured image of a patterned multilayer substrate obtained via a scanning electron microscope using a blur removal model and depth data according to one embodiment. [Figure 13]

[0028] A schematic diagram of an embodiment of a scanning electron microscope (SEM) according to one embodiment is shown. [Figure 14]

[0029] An embodiment of an electron beam inspection apparatus according to one embodiment is schematically shown. [Figure 15]

[0030] This is a block diagram of an exemplary computer system according to one embodiment. [Figure 16]

[0031] This is a schematic diagram of a lithography projection device according to one embodiment. [Figure 17]

[0032] This is a schematic diagram of another lithography projection apparatus according to one embodiment. [Figure 18]

[0033] This is a more detailed diagram of the apparatus shown in Figure 16, according to one embodiment. [Figure 19]

[0034] This is a more detailed diagram of the source collector module SO of the apparatus shown in Figures 17 and 18, according to one embodiment. [Modes for carrying out the invention]

[0014]

[0035] Integrated circuit (IC) chips used in devices (e.g., telephones, laptops, computer memory) contain complex circuit patterns. During the manufacturing of such circuit patterns, it is desirable to capture an image of the printed circuit pattern on the chip (also called a substrate) to determine whether the desired circuit pattern has been accurately printed. Often, the captured image is blurred, making it difficult to identify individual circuit features of the circuit pattern. In one example, deblurring of the captured image occurs because circuit features are formed on multiple layers of chips arranged vertically. Therefore, the blurring of the captured image is removed for better identification of individual circuit features. The captured image is deblurred by a deblurring model specifically trained for such complex applications.

[0015]

[0036] One method for capturing images of printed circuit patterns is to use a capture device that projects an electron beam onto the circuit pattern. The electrons of the electron beam are diffracted differently depending on the characteristics of the layers on which the circuit features of the circuit pattern are formed. In this specification, depth information for each layer is used to remove image blur. Depth information facilitates accurate modeling of the deblurring effect at different layer depths. For example, depth information can indicate that features in deeper layers appear blurred compared to the top layer. Thus, better deblurring of circuit pattern features located at different depths can be achieved, resulting in a more accurate and less blurred image, which in turn facilitates the precise identification of individual circuit features.

[0016]

[0037] While this document may specifically refer to the manufacture of ICs, it should be explicitly understood that the descriptions herein have many other possible applications. For example, the descriptions herein may be used in the manufacture of integrated optical systems, guidance and detection patterns for magnetic domain memory, liquid crystal display panels, thin-film magnetic heads, and the like. Those skilled in the art will understand that, in the context of such alternative applications, the terms “reticle,” “wafer,” or “die” herein should be considered interchangeable with the more general terms “mask,” “substrate,” and “target portion,” respectively. Substrates referred to herein may be processed before or after exposure, for example, with a track (e.g., a tool typically used to coat a resist layer on a substrate and develop the exposed resist) or a measuring or inspection tool. Where applicable, the disclosure herein may apply to such and other substrate processing tools. Furthermore, substrates may be processed multiple times, for example, to manufacture multilayer ICs, and the term “substrate” as used herein may also refer to a substrate that already contains multiple processed layers.

[0017]

[0038] The critical dimension (CD) of a device refers to 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. Naturally, one of the goals of device manufacturing is to faithfully reproduce the original design intent on the substrate (via patterning devices).

[0018]

[0039] In this document, the terms “radiation” and “beam” may be used to encompass all types of electromagnetic radiation, including ultraviolet radiation (e.g., having wavelengths of 365, 248, 193, 157, or 126 nm) and EUV (extreme ultraviolet radiation, e.g., having wavelengths in the range of approximately 5 to 100 nm).

[0019]

[0040] As used herein, the terms “mask” or “patterning device” can be broadly interpreted to refer to any general patterning device that can be used to impart a patterned cross-section to an incoming radiation beam, corresponding to a pattern to be generated on a target portion of a substrate. The term “light bulb” may also be used in this context. In addition to conventional masks (transmissive or reflective, binary, phase-shifted, hybrid, etc.), other examples of such patterning devices include: - Programmable mirror arrays. An example of such a device is a matrix-addressable surface having a viscoelastic control layer and reflective surfaces. The basic principle behind such a device is that (for example) the address area of ​​the reflective surface reflects incident radiation as diffracted radiation, while the non-addressed area reflects incident radiation as non-diffracted radiation. Using appropriate filters, the aforementioned non-diffracted radiation can be removed from the reflected beam, leaving only the diffracted radiation behind, so that the beam is patterned according to the addressing pattern of the matrix-addressable surface. The required matrix addressing can be carried out using appropriate electronic means. - Programmable LCD array. An example of such a structure is given by U.S. Patent No. 5,229,872, which is incorporated herein.

[0020]

[0041] As a brief introduction, Figure 1 shows an exemplary lithography projection apparatus 10A. The main components are a radiation source 12A (as discussed herein, the lithography projection apparatus itself does not need to have a radiation source), which may be a deep ultraviolet excimer laser source or other types of sources including an extreme ultraviolet (EUV) source; an illumination optical system that defines partial coherence (represented as sigma), which may include optical systems 14A, 16Aa, and 16Ab for shaping the radiation from the source 12A; a patterning device 18A; and a transmission optical system 16Ac for projecting an image of the pattern of the patterning device onto the substrate surface 22A. An adjustable filter or aperture 20A at the pupil plane of the projection optical system may limit the range of beam angles that strike the substrate surface 22A, where the maximum possible angle is defined by the numerical aperture NA = n sin(Θmax) of the projection optical system, where n is the refractive index of the medium between the substrate and the last element of the projection optical system, and Θmax is the maximum angle of the beam leaving the projection optical system that can still strike the substrate surface 22A.

[0021]

[0042] In a lithography projection apparatus, a source provides illumination (i.e., radiation) to a patterning device, and a projection optical system guides and shapes the illumination onto the substrate via the patterning device. The projection optical system may include at least some of components 14A, 16Aa, 16Ab, and 16Ac. The spatial image (AI) is the radiation intensity distribution at the substrate level. A resist layer on the substrate is exposed, and the spatial image is transferred to the resist layer as a potential "resist image" (RI). The resist image (RI) can be defined as the spatial distribution of the solubility of the resist in the resist layer. A resist model can be used to calculate the resist image from the spatial image, an example of which can be found in U.S. Patent Application Publication 2009 / 0157360, the disclosure of which is incorporated herein by reference in its entirety. The resist model is concerned only with the properties of the resist layer (e.g., the effects of chemical processes occurring during exposure, PEB, and development). The optical properties of a lithography projection system (e.g., the properties of the source, patterning device, and projection optics) determine the spatial image. Since the patterning device used in a lithography projection system can be changed, it may be desirable to decouple the optical properties of the patterning device from the optical properties of the rest of the lithography projection system, including at least the source and projection optics.

[0022]

[0043] In chip manufacturing (also known as patterning process or semiconductor manufacturing), for example, the target pattern of a chip (e.g., a circuit pattern) can be printed on multiple layers on a substrate. Each layer has specific features (e.g., lines, contact holes, bars, etc.) of the target pattern (e.g., a circuit pattern). These features, when connected to each other, provide the desired electrical or logical function of the chip or circuit. The features can be connected to each other via multiple layers to form the target pattern of the chip.

[0023]

[0044] In many cases, patterned substrates are inspected or measured using a scanning electron microscope (SEM) to examine the printability of the target pattern in detail. SEM images are examined to ensure that the target pattern of the chip is printed on the substrate within acceptable threshold limits for the physical properties associated with the features. If the printability is outside the acceptable threshold limits, it negatively impacts the chip manufacturing yield. Based on the inspection, one or more processes in chip manufacturing may be adjusted to improve printability and chip manufacturing yield.

[0024]

[0045] Typically, the high landing energy (HLE) setting of a SEM tool is used to measure patterns at high depths (e.g., in the third or fourth layer located vertically downwards from the top layer) for inspection and measurement purposes. The HLE SEM image signal is primarily derived from backscattered electrons (BSE). The BSE signal causes a lot of blurring in the SEM image. For example, based on the diffraction characteristics of BSE, features on the bottom layer (e.g., at the maximum depth from the top surface of the substrate) have the greatest diffraction effect in the SEM image, which is seen in the form of edge blurring. Therefore, deblurring algorithms can be used to obtain a sharper SEM image. For example, a deblurred image is one in which some features or feature boundaries are blurred. On the other hand, after deblurring the image, the feature boundaries have sharper or more defined edges.

[0025]

[0046] Referring to Figures 2A-2F, examples of blurring caused by BSE diffraction effects on different layers of the substrate are shown. Figure 2A shows a target pattern TP1 (e.g., in GDS format) containing multiple features (e.g., contact holes CH (only a few holes are labeled for illustrative purposes)). Figure 2B shows a first pattern L1 corresponding to the target pattern TP1. In this example, the first pattern L1 is printed on a first layer of the substrate (e.g., the top layer). The first pattern L1 may be formed at a first depth (e.g., 0 nm) in the substrate. The boundaries of the contact holes in the first pattern L1 are sharp. For example, when the contact holes of TP1 are superimposed on the first pattern L1, the intensity of the pixels (in L1) at the hole boundaries shows minimal or no change. Thus, the contact holes in the first pattern L1 can be accurately identified. However, as the depth of the layers on the substrate increases (for example, vertically downwards from the top layer), the edges of features (e.g., contact holes) become increasingly blurred. For example, the pixel intensity at the edges of features changes significantly, making it difficult to accurately distinguish the boundaries of features in deeper layers. Exemplary blurring of features at greater depths is shown in Figures 2C, 2D, and 2E.

[0026]

[0047] Figure 2C shows a second pattern L2 formed on a second layer L2 at a second depth (e.g., 2 nm vertically below the first layer). Compared to the feature edges in the first pattern L1, the edges of the features (black circles) are blurred. Figure 2D shows a third pattern L3 formed on a third layer L3 at a third depth (e.g., 5 nm vertically below the first layer). Compared to the feature edges in the second pattern L2, the edges of the features (black circles) are blurred. Similarly, Figure 2D shows a fourth pattern L4 formed on a fourth layer L3 at a fourth depth (e.g., 8 nm vertically below the first layer). Compared to the feature edges in the third pattern L3, the edges of the features (black circles) are blurred. Therefore, referring to the image L4-TP1 in Figure 2E, it is unclear where the feature edges in L4 actually are when the target pattern TP1 is superimposed on the fourth pattern L4.

[0027]

[0048] Currently, there are several challenges in methods for removing blur and noise from HLE SEM images. For example, the feature boundaries in deblurred HLE SEM images are unclear and inaccurate. Another challenge is aliasing, which refers to image distortion that occurs when the reconstructed signal from the sample differs from the original signal, resulting in inaccurate edge determination. In SEM images of patterned multilayer substrates, BSE causes diffraction at the first depth of the first layer that differs from diffraction at the second depth of the second layer, and this diffraction makes edge blurring more complex. Conventional Monte Carlo simulations used to analyze diffraction effects are time-consuming. Ground truth images cannot be used to improve one or more aspects of the patterning process, for example, to improve the accuracy of the process model involved in the determination of feature CDs, because obtaining clean and accurate HLE SEM images is difficult.

[0028]

[0049] This disclosure provides a method for deblurring a captured image based on depth data that causes the deblurring of the captured image. In one embodiment, the deblurring model is trained using the effect of feature depth from the top layer of the patterned substrate. For example, the effect of feature depth can be observed at the edges of the features. As the depth of the features from the top layer increases, the edges of the features become more blurred due to the BSE signal being weaker compared to the BSE signal from the top layer.

[0029]

[0050] In one embodiment, a trained deblurring model can be used in one or more lithography and measurement applications. For example, a captured image of an actual patterned substrate having memory circuit features can be deblurred via the deblurring model. From the deblurred image, the memory circuit features can be identified and accurately extracted. Such extracted features can then be provided to train more accurate process models related to lithography (e.g., resist models, optical proximity correction (OPC) related models, etc.). In another application, more accurate feature geometry (e.g., shape and size) can be extracted from the deblurred image of the patterned substrate, thereby improving the accuracy of measurement data. Furthermore, the deblurred image can improve the reliability of inspection of the patterned substrate.

[0030]

[0051] Figure 3 is a flowchart of Method 300 for training a deblurring model configured to remove blur from a captured image of a patterned substrate. To better understand the method, this consideration uses feature edges as an exemplary characteristic affected by, for example, the depth of the features from the top layer. Deblurring of the captured image allows for a more accurate identification of feature characteristics (e.g., feature edges). In one embodiment, the process of training the deblurring model is considered in more detail with respect to the following steps P301, P303, and P305.

[0031]

[0052] Process P301 includes obtaining a simulated image 302 of the substrate corresponding to the target pattern TP via a simulator that uses a target pattern TP from which a pattern on the substrate is derived. In one embodiment, the target pattern TP may be formed on multiple layers of the substrate arranged vertically from top to bottom, each layer having one or more features corresponding to the target features of the target pattern. For example, a first target feature is formed on a first layer of the substrate, and a second target feature is formed on a second layer located below the first layer of the substrate.

[0032]

[0053] In one embodiment, the target pattern TP is presented in the form of a polygon-based hierarchical data format. For example, the polygon-based data format may be a graphics data system (GDS) format, a color image, a vector format, or other data representation. In one embodiment, the target pattern TP includes geometric data associated with a first target feature and a second target feature. The geometric data may be, for example, the desired shapes of the first and second target features within the target pattern TP, as well as the target positions of the edges of the first and second target features. In one embodiment, each target feature is associated with a layer of substrate on which each target feature can be formed.

[0033]

[0054] In one embodiment, the simulated image 302 includes noise, such as variations in the image's brightness or color information. In one embodiment, obtaining the simulated image 302 further includes extracting noise from the captured image of the patterned substrate and adding noise to the simulated image 302. The noise in the captured image may be, for example, specific to the capture device.

[0034]

[0055] In one embodiment, the simulator includes a model that is a function of the physical properties of the substrate on which the target pattern TP is printed. The simulator is configured to generate a simulated image 302 by adjusting the BSE properties of the electron beam of a capture device (e.g., SEM). When adjusting the BSE properties, different diffraction effects associated with the target pattern can be taken into account, thereby making it possible to determine feature properties (edges, size, grayscale values, etc.) in each layer of the substrate. In one embodiment, the physical properties of the substrate can be the material of a particular layer, the thickness of a particular layer, resist process parameters, etching process parameters, or a combination thereof. The model used in the simulator can be a physics-based model that models diffraction, the physical properties of electron absorption / diffraction by a particular layer, etc. The model can be a statistical model fitted based on BSE data.

[0035]

[0056] In one embodiment, obtaining a simulated image 302 involves simulating a model that generates the simulated image 302 through a Monte Carlo simulation process. During the Monte Carlo simulation process, one or more BSE characteristics, layer depths, etc., can be adjusted to generate the simulated image 302. The simulated image 302 can represent a real image of a patterned substrate captured via a capture device (e.g., a scanning electron microscope). In one embodiment, obtaining a simulated image 302 involves simulating a double Gaussian model configured to generate the simulated image 302 based on depth data.

[0036]

[0057] Figure 7 shows an example of obtaining a simulated image from a simulator using a target pattern. An exemplary target pattern 702 (e.g., a DRAM circuit pattern) includes multiple features formed on different layers on a substrate. The target pattern 702 includes a first target feature F1 (e.g., a horizontal line) formed on a first layer, a second target feature F2 (e.g., a vertical line) formed on a second layer, a third feature F3 (e.g., a sloped bar) formed on a third layer, and a fourth feature F4 (e.g., a circle) formed on a fourth layer.

[0037]

[0058] In one embodiment, the target pattern 702 is input to a simulator 704 configured to generate a simulated image that mimics an actual patterned substrate. For example, the simulator 704 includes a Monte Carlo simulation of a model. The model generates a simulated image of the substrate as a function of diffraction effects in different layers of the substrate. For example, in one embodiment, the model can be configured to assign / modify the number of electrons projected onto the substrate. For example, the number of electrons could be about 2000, about 2500, about 3000, etc. The model predicts that there may be about 140 backscattered electrons when the electrons hit a feature in the first layer. Furthermore, the model can be configured to take inputs for the electron landing energy (e.g., 10 keV, 20 keV, etc.) and the electron density (e.g., about 2.4). Beyond these exemplary settings, the simulator 704 may be configured to include additional properties that affect the diffraction of electrons after they hit the target feature.

[0038]

[0059] In one embodiment, the simulator 704 outputs a simulated image 706 that mimics an image of an actual patterned substrate. In one embodiment, the simulated image 706 is a pixelated grayscale image, where the intensity of each pixel is the result of the simulator 704 predicting a signal from, for example, a BSE. Since the simulated image is used as a training dataset, the deblurring model can be trained to cover a large number of patterns compared to a training dataset that includes, for example, actual SEM images. This is because capturing a large number of SEM images can damage the patterned substrate, affecting the yield of the patterning process and slowing down the semiconductor manufacturing speed.

[0039]

[0060] Figure 9 shows another example of generating a simulated image. In this example, the simulated image 706 (generated through a simulator, e.g., Monte Carlo simulation, as discussed above) is modified by adding image noise 906. For example, image noise 906 can be extracted from an actual SEM image or generated statically as random noise. In one embodiment, noise 906 can be extracted by applying a noise filter to an actual SEM image. Adding noise to the simulated image generates a noisy simulated image 706'. In one embodiment, the noisy simulated image 706' may also be referred to as simulated image 706. In this disclosure, the noisy simulated image 706' may be interchangeably referred to as simulated image 706.

[0040]

[0061] In one embodiment, the robustness of the trained deblurring model is improved by using a simulated image 706' (including noise) as training data. For example, the trained deblurring model can produce reliable results even when the input image (e.g., an actual SEM image) has considerable noise. For example, a noisy image may result from poor acquisition conditions, measurement settings, etc.

[0041]

[0062] Process P303 determines edge extent data ERD for features on the substrate corresponding to the first and second target features of the target pattern TP, based on depth data DEP associated with each layer of the substrate. The depth data DEP characterizes the edge blur of the features on the substrate as a function of the depth of each feature from the top layer of the substrate.

[0042]

[0063] In one embodiment, depth data DEP includes at least one of the following: the depth of a feature from the top layer of the substrate, the material used for a particular layer of the substrate, and the diffraction behavior of the feature at a given depth. For example, depth data DEP may include a first depth of a first layer located vertically downward from the top layer of the substrate, a second depth of a second layer located vertically downward from the top layer, material data associated with the first and second layers of the substrate, or diffraction behavior associated with the first and second features on the substrate corresponding to the first and second target features of the target pattern TP, respectively.

[0043]

[0064] In one embodiment, the edge extent data (ERD) includes a range of edge locations for the features on the substrate corresponding to each feature in the target pattern TP. In one embodiment, determining the edge extent data (ERD) involves running a model configured to calculate the edge changes of the features on the substrate corresponding to each feature of the target pattern TP printed on the substrate. In one embodiment, the edge extent data (ERD) is represented as an image of the target pattern TP complemented by the edge extent data (ERD) of each feature in the target pattern TP.

[0044]

[0065] Figures 8A and 8B show exemplary target patterns and corresponding edge range data associated with the depth of features within the target pattern. Referring to Figure 8A, the exemplary target pattern 702 (e.g., a DRAM circuit pattern) includes multiple features formed on different layers on the substrate. As previously discussed, the target pattern 702 includes a first target feature F1 (e.g., a horizontal line) formed on a first layer of the substrate, a second target feature F2 (e.g., a vertical line) formed on a second layer of the substrate, a third feature F3 (e.g., a sloping bar) formed on a third layer of the substrate, and a fourth feature F4 (e.g., a circle) formed on a fourth layer of the substrate.

[0045]

[0066] In this example, the first layer can be considered the top layer. The second layer is located at a depth (e.g., 5 nm) vertically below the first layer. The third layer is located at a depth (e.g., 10 nm) vertically below the first layer. The fourth layer is located at a depth (e.g., 15 nm) vertically below the first layer. Thus, features F1, F2, F3, and F4 are printed on their respective layers of the substrate. When an image of the patterned substrate is captured, the image of the bottom layer (e.g., with feature F4 at the maximum depth) has the greatest diffraction effect due to the characteristics of BSE backscatter electrons (e.g., the edges of feature F4 are more blurred). In one embodiment, the change in characteristics relates to such depth data, for example, based on the depth of each feature (e.g., F1, F2, F3, F4). Based on the depth data of each feature, edge range data for each feature can be determined. The edge range data characterizes the range in which the edges of the feature may be located on the substrate.

[0046]

[0067] Figure 8B is an image representation of the edge extent data 702ER generated for the target pattern 702. In the edge extent data 702ER, the thickness of each feature represents the extent of that feature. For example, the thicknesses of lines E1 (corresponding to feature F1), E2 (corresponding to feature F2), E3 (corresponding to feature F3), and E4 (corresponding to feature F4) indicate the amount by which diffraction at the edges of features F1, F2, F3, and F4 is affected by the depth data. For example, line E4 is associated with the largest change in the BSE diffraction signal. When such edge extent data E1, E2, E3, and E4 are used as a training dataset, more accurate determination of feature edges can be made in very blurred areas.

[0047]

[0068] In one embodiment, the edge range data 702ER may be determined using a model (similar to, for example, the one used in the simulator 704 considered with respect to Figure 7). The model is configured to determine the edge range data for a feature on the substrate based on depth data, such as material data for each layer, diffraction properties associated with the material and depth, etc. For example, the material of feature F1 is chromium, the material of feature F2 is copper, the material of feature F3 is tungsten, and the material of feature F4 is a polyresin material. The materials considered herein are merely illustrative and do not limit the scope of this disclosure. The layer material may be SiO, Si, or other materials used in semiconductor manufacturing. In one embodiment, the model may be a function (or mapping) between the edge range and the layer depth and layer material. Such a function (or mapping) may be established, for example, by correlated real data of features, material, and depth on a patterned substrate.

[0048]

[0069] Process P305 involves using a simulated image 302 and edge range data ERD for features on the substrate corresponding to the target pattern TP as training data to adjust the parameters of a basic model and generate a deblurring model DBM. The deblurring model DBM uses the edge range data ERD associated with the captured image to generate a deblurred image of the captured image of the patterned substrate. This disclosure is not limited to any particular type of model, as long as the model is configured to take edge range data and a captured image as input to generate a deblurred image of the captured image.

[0049]

[0070] In one embodiment, the base model or deblurring model DBM is a machine learning model that includes weights and biases as model parameters. During the training process, the weights and biases of the base model are continuously updated based on the training data. At the end of training, the base model is referred to as the deblurring model. In one embodiment, the deblurring model DBM is a convolutional neural network (e.g., CNN) or a deep convolutional network (e.g., DCNN). The model parameters include the weights and biases of one or more layers of the deep convolutional network.

[0050]

[0071] In one embodiment, the deblurring model DBM is a neural network that includes a feature vector containing values ​​representing features of a target pattern TP, and an attention vector containing values ​​relating to the depth associated with features printed on the substrate, and is configured to be computed with the feature vector. In one embodiment, the attention vector includes any value in the range of 0 to 1, or a binary value of 0 or 1.

[0051]

[0072] In one embodiment, the machine learning model is structured to multiply the attention vector by the feature vector such that depth-related weights are assigned to the edges of specific features in the feature vector by the attention vector. For example, a first target feature associated with a first layer of the substrate is multiplied by a higher attention value compared to the attention value multiplied by a second target feature associated with a second layer of the substrate.

[0052]

[0073] Figure 10 is an image representation of an exemplary structure of a deblurring model DBM configured to receive an image (e.g., a SEM image or simulated image of a target pattern TP) and depth-related data (e.g., edge range data ERD). As shown in the figure, each input may be represented as a feature vector FV. For example, the feature vector may be a vector representation of the captured image (e.g., a simulated image or an actual SEM image). In one embodiment, the feature vector FV includes information such as the position and intensity of pixels. In one embodiment, the intensity values ​​indicate features of the target pattern (e.g., TP). Optionally, another layer is provided that contains statistical information of the feature vector.

[0053]

[0074] In one embodiment, the deblurring model also includes a focus vector AV, which contains values ​​related to the depth associated with the features printed on the substrate. In this example, in one layer, the focus vector contains any value in the range of 0 to 1 (or other values, e.g., 1 to 100). For example, in a top-down view vector AV, the first depth is assigned the value 0.95, the second depth the value 0.8, the third depth the value 0.6, and the fourth depth the value 0.5. In one embodiment, edge range data (e.g., ERD) is used to generate focus values ​​(or weights), which are then applied to a feature map (e.g., a transformed SEM image in a particular layer of a CNN).

[0054]

[0075] In one embodiment, the feature vector of the simulated or captured image is calculated with the attention vector AV (e.g., generated from edge range data ERD). Therefore, the feature vector FV is converted to another vector FVX. As a result, the converted feature vector FVX has the depth data described.

[0055]

[0076] Figure 11 shows an example of training a deblurring model DBM using a simulated image 706' (which is noisy) and edge range data 702ER associated with the target pattern TP. The deblurring model DBM generates a deblurred image 1101 with clearly defined boundaries of features within the target pattern TP (not shown in Figure 11). Since the feature boundaries can be clearly identified, the deblurring model DBM is considered trained.

[0056]

[0077] Figure 4 is a flowchart of method 400 for removing blur from a captured image of a patterned substrate. For example, a measurement tool (e.g., SEM image) may be used to capture an image of the patterned substrate. Exemplary embodiments of this method include processes P401 and P403. The processes may be executed via one or more processors of the computer system discussed herein. In one embodiment, the process is carried out on the processor of the measurement tool (e.g., SEM tool).

[0057]

[0078] Process P401 involves inputting the captured image CI and edge range data ERD of the patterned substrate associated with the target pattern into the deblurring model DBM. As discussed above, the deblurring model DBM is trained based on the edge range data ERD associated with the target pattern features at a specific depth.

[0058]

[0079] As discussed earlier, the edge extent data (ERD) for features on the substrate corresponding to features in the target pattern is determined based on depth data associated with the target pattern and the substrate. The depth data includes the first depth of a first layer located vertically downward from the top layer of the substrate, the second depth of a second layer located vertically downward from the top layer, material data associated with the first and second layers of the substrate, the diffraction behavior associated with the first and second features on the substrate corresponding to the first and second target features of the target pattern TP, respectively, or a combination thereof.

[0059]

[0080] In one embodiment, the edge extent data (ERD) includes a range of edge locations for the features on the substrate corresponding to each feature in the target pattern. In one embodiment, determining the edge extent data (ERD) involves running a model configured to calculate the edge changes of the features on the substrate corresponding to each feature in the target pattern. In one embodiment, the edge extent data (ERD) is represented as an image of the target pattern complemented by the edge extent data (ERD) of each feature in the target pattern.

[0060]

[0081] Process P403 involves removing blur from the captured image CI by executing a deblurring model. The resulting deblurred image DBCI has sharper feature edges even at deeper layers (e.g., 10nm, 20nm, and 30nm depths from the top of the substrate).

[0061]

[0082] Figure 12 shows an example of a method for deblurring an actual captured SEM image. Deblurring involves inputting a captured image SEM1 of a patterned substrate associated with a target pattern (e.g., the use of TP for patterning the substrate) and edge range data 702ER into a deblurring model DBM. As discussed above, the deblurring model DBM is trained on edge range data ERD associated with the target pattern features at a specific depth. The captured image is then blurred by running the deblurring model DBM. The deblurring model DBM outputs a deblurred image dbSEM1.

[0062]

[0083] Figure 5 is an alternative flowchart of method 500 for removing blur from the captured image of a patterned substrate. In this embodiment, the method includes processes P501, P503, P505, and P507, as discussed below.

[0063]

[0084] Process P501 includes receiving a captured image CI of a patterned substrate. For example, the captured image CI can be received via a measurement tool (e.g., Figures 13 and 14). The patterned substrate may be a patterned multilayer substrate. Therefore, high landing energies may be used to capture an image showing the multilayer pattern within the image. As discussed herein, the captured image CI is blurred due to backscattered electrons having a weak signal towards deeper layers (e.g., depths of 5 nm, 10 nm, 20 nm, the bottom layer, etc.). For example, features on deeper layers appear blurred in the captured image CI. Therefore, deblurring of the captured image CI is performed.

[0064]

[0085] Process P503 includes inputting the captured image CI into a deblurring model. The deblurring model is trained by processes P301, P303, and P305 (in Figure 3). Process P505 includes receiving output from the deblurring model using the captured image CI and edge extent data for features on the patterned substrate. The output is a deblurred captured image CI. Process P507 includes generating the deblurred captured image CI on a user interface for display. In one embodiment, the deblurred version of the captured image CI may be generated as a vector that can be input into other models involved in the patterning process. Thus, the deblurred version of the captured image CI can be used to improve multiple aspects of one of the patterning processes, such as improving OPC, dose amount, focus, etc.

[0065]

[0086] Figure 6 is an alternative flowchart of method 600 for removing blur from the captured image of a patterned substrate. In this embodiment, the method includes processes P601 and P603, as discussed below.

[0066]

[0087] Process P601 includes identifying features in the captured image CI based on a target pattern TP6 and depth data DD associated with each layer of the substrate. In one embodiment, the depth data includes data such as depth, material, and diffraction characteristics at a specific depth of the substrate. In one embodiment, the depth data DD includes feature characteristics derived from the depth data DD. For example, the feature characteristics may be the edge range of each feature in a particular layer. Process P603 includes deblurring the captured image CI by removing the blur of each feature based on the target pattern TP6 and depth data DD6. After deblurring, a deblurred image DBCI of the captured image CI is obtained. For example, Figure 12 shows an example of a deblurred image dbSEM1.

[0067]

[0088] As discussed herein, an example of a deblurring model is a machine learning model. Both unsupervised and supervised machine learning models can be used to generate deblurred images from input noisy images, such as SEM images of patterned substrates. Without limiting the scope of the present invention, the application of supervised machine learning algorithms is described below.

[0068]

[0089] Supervised learning is a machine learning task that infers a function from labeled training data. The training data consists of a set of training examples. In supervised learning, each example is a pair with an input object (typically a vector) and a desired output value (also called a watch signal). A supervised learning algorithm analyzes the training data and generates an inferred function that can be used to map new examples. The optimal scenario would be for the algorithm to correctly determine the class label of an unseen instance. This requires the learning algorithm to generalize to unseen situations in a "reasonable way" from the training data.

[0069]

[0090] x i , is the feature vector of the i-th example, and y i However, the labels (i.e., classes) are {(x1,y1), (x2,y2), ..., (x N ,y NGiven a set of N training examples of the form )}, the learning algorithm finds a function g:X→Y, where X is the input space and Y is the output space. A feature vector is an n-dimensional vector of numerical features representing an object. Many algorithms in machine learning require such representations because numerical representations of objects facilitate processing and statistical analysis. When representing an image, feature values ​​may correspond to pixels in the image; when representing text, feature values ​​may correspond to term occurrence frequencies. The vector space associated with these vectors is often called the feature space. The function g is an element of some space of possible functions G, usually called the hypothetical space. g is the highest score:

number

number

[0070]

[0091] G and F can be in either function space, but many learning algorithms use probabilistic models where g takes the form of a conditional probabilistic model g(x)=P(y|x), or f takes the form of a joint probabilistic model f(x,y)=P(x,y). For example, Naive Bayes and linear discriminant analysis are joint probabilistic models, while logistic regression is a conditional probabilistic model.

[0071]

[0092] There are two basic methods for choosing between f and g: empirical risk minimization and structural risk minimization. Empirical risk minimization seeks the function that best fits the training data. Structural risk minimization includes a penalty function to control the bias / variance tradeoff.

[0072]

[0093] In both cases, the training sets are independent and identically distributed pairs (x i ,y i It is assumed that we have a sample of ). To measure how well the function fits the training data, we use the loss function L:

number

number

number

[0073]

[0094] The risk R(g) of the function g is defined as the expected loss of g.

number

[0074]

[0095] Exemplary supervised learning models include decision trees, ensemble methods (bagging, boosting, random forests), k-NNs, linear regression, naive Bayes, neural networks, logistic regression, cognitive models, support vector machines (SVMs), relational vector machines (RVMs), and deep learning.

[0075]

[0096] SVM is an example of a supervised learning model that can analyze data, recognize patterns, and be used for classification and regression analysis. Given a set of training examples each marked as belonging to one of two categories, the SVM training algorithm constructs a model that assigns new examples to one or the other category and makes it a non-probabilistic binary linear classifier. The SVM model is a representation of examples as points in space, mapped such that examples from separate categories are divided by the widest possible clear gap. New examples are then mapped into the same space and predicted to belong to a category based on which side of the gap they fall on.

[0076]

[0097] In addition to performing linear classification, SVMs can efficiently perform non-linear classification using the so-called kernel method, which can implicitly map their inputs into a high-dimensional feature space.

[0077]

[0098] The kernel method requires a user-specified kernel, i.e., a similarity function on pairs of data points in their raw representation. The name kernel method derives from the use of a kernel function, which allows it to operate by computing simply the inner product between the images of all pairs of data in the feature space, rather than ever computing the coordinates of the data in that space. This operation is often computationally cheaper than explicit computation of the coordinates. This technique is called the "kernel trick".

[0078]

[0099] The effectiveness of SVMs depends on the choice of kernel, the kernel's parameters, and the soft margin parameter C. A common choice is the Gaussian kernel, which has a single parameter γ. The best combination of C and γ is often a sequence of exponentially increasing C and γ (e.g., C ∈ {2 -5 、2 -4 、…、2 15 、2 16}; γ ∈ {2 -15 、2 -14 、…、24 , 2 5 The selection is made by a grid search using}) (also known as a "parameter sweep").

[0079]

[0100] Grid search is an extensive search of a manually specified subset of the hyperparameter space of a learning algorithm. Grid search algorithms are typically guided by certain performance metrics, measured by cross-validation against a training set or evaluation against a provided validation set.

[0080]

[0101] Each combination of parameter selections may be checked using cross-validation, and the parameter with the best cross-validation accuracy is selected.

[0081]

[0102] Cross-validation, sometimes called rotation estimation, is a model validation technique that evaluates how the results of a statistical analysis generalize to an independent dataset. It is primarily used in situations where the goal is prediction and you want to estimate how accurately a predictive model will actually perform. In a prediction problem, a model is typically given a dataset of known data on which it is trained (training dataset) and a dataset of unknown data (or unseen data) on which the model is tested (test dataset). The goal of cross-validation is to define a dataset for "testing" the model during the training phase (i.e., a validation dataset) to limit issues such as overfitting and to give insights into how the model generalizes to an independent dataset (i.e., an unknown dataset from a real-world problem). A single round of cross-validation involves segmenting a data sample into complementary subsets, performing the analysis on one subset (called the training set), and validating the analysis on the other subset (called the validation set or test set). To reduce variability, multiple rounds of cross-validation are performed using different segmentations, and the validation results across those rounds are averaged.

[0082]

[0103] Next, the final model, which can be used for testing and classifying new data, is trained on the entire training set using the selected parameters.

[0083]

[0104] Another example of supervised learning is regression. Regression infers the relationship between a dependent variable and one or more independent variables from a set of values ​​for the dependent variable and the corresponding values ​​for the independent variables. Regression can estimate the conditional expectation of the dependent variable given the independent variables. The inferred relationship is sometimes called the regression function. The inferred relationship can be probabilistic.

[0084]

[0105] In one embodiment, a system is provided that can generate a deblurred image using a model DBM after the system has captured an image of a patterned substrate. In one embodiment, the system may be, for example, the SEM tool of Figure 13 or the inspection tool of Figure 14, configured to include the model DBM discussed herein. For example, the measurement tool includes an electron beam generator for capturing an image of a patterned substrate and one or more processors including a deblurred model. One or more processors are configured to run a trained model using the captured image and depth data (e.g., edge range data) of the target pattern as input to generate a deblurred image of the captured image. As previously mentioned, the deblurred model DBM may be a convolutional neural network.

[0085]

[0106] Furthermore, in one embodiment, one or more processors may be configured to update the deblurring model based on a captured image of the patterned substrate. In one embodiment, updating the deblurring model includes running the deblurring model using the captured image to generate a deblurred image and updating one or more parameters of the deblurring model based on a comparison of the deblurred image with a reference deblurred image.

[0086]

[0107] In one embodiment, the deblurred image can be used to improve the patterning process. The deblurred image can be used to simulate the patterning process to predict, for example, contours, CD, edge placement (e.g., edge placement errors), etc., in the resist and / or etched image. The purpose of the simulation is to accurately predict, for example, the edge placement and / or spatial image intensity gradient and / or CD of the printed pattern. These values ​​can be compared to the intended design, for example, to correct the patterning process or to identify locations where defects are expected to occur. The intended design is generally defined as a pre-OPC design layout and can be provided in a standard digital file format such as GDSII or OASIS or other file format.

[0087]

[0108] In some embodiments, the inspection or measurement device may be a scanning electron microscope (SEM) that obtains an image of a structure (e.g., part or all of the structure of a device) exposed or transferred onto a substrate. Figure 13 illustrates an embodiment of the SEM tool. The primary electron beam EBP emitted from the electron source ESO is focused by a condenser lens CL and then passes through a beam deflector EBD1, an E×B deflector EBD2, and an objective lens OL to illuminate the substrate PSub on the substrate table ST at the focal point.

[0088]

[0109] When the electron beam EBP is irradiated onto the substrate PSub, secondary electrons are generated from the substrate PSub. These secondary electrons are deflected by the E×B deflector EBD2 and detected by the secondary electron detector SED. For example, a two-dimensional electron beam image can be obtained by detecting electrons generated from the sample in synchronization with a two-dimensional scan of the electron beam by the beam deflector EBD1, or by repeatedly scanning the electron beam EBP by the beam deflector EBD1 in the other direction of the X or Y direction, along with the continuous movement of the substrate PSub by the substrate table ST in the X or Y direction.

[0089]

[0110] The signal detected by the secondary electron detector (SED) is converted into a digital signal by an analog-to-digital (A / D) converter (ADC), and the digital signal is transmitted to the image processing system (IPU). In one embodiment, the image processing system (IPU) may have memory (MEM) for storing all or part of the digital image for processing by the processing unit (PU). The processing unit (PU) (e.g., specially designed hardware, or a combination of hardware and software) is configured to convert or process the digital image into a dataset representing the digital image. Furthermore, the image processing system (IPU) may have storage medium (STOR) configured to store the digital image and the corresponding dataset in a reference database. A display device (DIS) may be connected to the image processing system (IPU), so that the operator can perform the necessary operations on the instrument with the help of a graphical user interface.

[0090]

[0111] As described above, SEM images can be processed to extract contours that depict the edges of objects representing device structures within the image. These contours are quantified using metrics such as CD. Thus, images of device structures are typically compared and quantified using simple metrics such as the distance between edges (CD) or the simple pixel difference between images. Typical contour models that detect the edges of objects in an image to measure CD use image gradients. Indeed, these models rely on strong image gradients. However, in reality, images are usually noisy and have discontinuous boundaries. Techniques such as smoothing, adaptive thresholding, edge detection, erosion, and expansion can be used to process the results of image gradient contour models to deal with noisy and discontinuous images, but these techniques ultimately lead to low-resolution quantification of high-resolution images. Thus, in most cases, mathematical manipulation of images of device structures to reduce noise and automate edge detection leads to a loss of image resolution, and thereby a loss of information. Hence the result is low-resolution quantification, which becomes a simple representation of a complex, high-resolution structure.

[0091]

[0112] Therefore, it is desirable to have a mathematical representation of a structure (e.g., circuit features, alignment marks, or measurement target portions (e.g., grid features)) that is generated or expected to be generated using a patterning process, regardless of whether the structure is in a potential resist image, in a developed resist image, or transferred, for example, by etching, to a layer on the substrate that can represent the general shape of the structure while maintaining resolution. In the context of lithography or other patterning processes, the structure may be a device or part thereof under manufacture, and the image may be a SEM image of the structure. In some cases, the structure may be a feature of a semiconductor device, such as an integrated circuit. In this case, the structure may be referred to as a pattern or a desired pattern containing multiple features of the semiconductor device. Depending on the circumstances, the structure may be an alignment mark or a part thereof (e.g., a grid of alignment marks) used in an alignment measurement process to determine the alignment between an object (e.g., a substrate) and another object (e.g., a patterning device), or a measurement target or a part thereof (e.g., a grid of a measurement target) used to measure parameters of a patterning process (e.g., overlay, focus, dose, etc.). In one embodiment, the measurement target is, for example, a diffraction grating used to measure the overlay.

[0092]

[0113] Figure 14 schematically shows a further embodiment of the inspection apparatus. The system is used to inspect a sample 90 (such as a substrate) on a sample stage 88 and includes a charged particle beam generator 81, a condenser lens module 82, a probe-forming objective lens module 83, a charged particle beam deflection module 84, a secondary charged particle detector module 85, and an image forming module 86.

[0093]

[0114] A charged particle beam generator 81 generates a primary charged particle beam 91. A condenser lens module 82 focuses the generated primary charged particle beam 91. A probe forming an objective lens module 83 focuses the focused primary charged particle beam onto a charged particle beam probe 92. A charged particle beam deflection module 84 scans the formed charged particle beam probe 92 across the surface of an area of ​​interest on a sample 90 fixed on a sample stage 88. In one embodiment, the charged particle beam generator 81, the condenser lens module 82, and the probe-forming objective lens module 83, or equivalent designs, substitutes, or any combination thereof, together form a charged particle beam probe generator that generates a charged particle beam probe 92 for scanning.

[0094]

[0115] The secondary charged particle detector module 85 detects secondary charged particles 93 (which may also include other charged particles reflected or scattered from the sample surface) emitted from the sample surface and generates a secondary charged particle detection signal 94 when struck by the charged particle beam probe 92. The image forming module 86 (e.g., a computer device) is coupled with the secondary charged particle detector module 85 to receive the secondary charged particle detection signal 94 from the secondary charged particle detector module 85 and, accordingly, forms at least one scan image. In one embodiment, the secondary charged particle detector module 85 and the image forming module 86, or equivalent designs, substitutes, or any combination thereof, together form an image forming apparatus that forms a scan image from detected secondary charged particles emitted from a sample 90 struck by the charged particle beam probe 92.

[0095]

[0116] In one embodiment, the monitoring module 87 is coupled to the image forming module 86 of the image forming apparatus to monitor and control the patterning process and / or derive parameters for the design, control, and monitoring of the patterning process using a scanned image of a sample 90 received from the image forming module 86. Therefore, in one embodiment, the monitoring module 87 is configured or programmed to perform the methods described herein. In one embodiment, the monitoring module 87 includes a computer device. In one embodiment, the monitoring module 87 includes a computer program for providing the functions described herein, encoded on a computer-readable medium forming or located within the monitoring module 87.

[0096]

[0117] In one embodiment, similar to the electron beam inspection tool in Figure 13 that uses a probe to inspect a substrate, the electron current in the system in Figure 14 is significantly larger than, for example, a CD-SEM as depicted in Figure 13, so the probe spot is sufficiently large, and as a result, the inspection speed may be fast. However, the resolution may not be as high as that of a CD-SEM due to the large probe spot. In one embodiment, the inspection apparatus discussed above may be a single-beam or multi-beam apparatus, without limiting the scope of this disclosure.

[0097]

[0118] For example, SEM images from the systems in Figure 13 and / or Figure 14 may be processed to extract contours that represent the device structure and define the edges of objects within the image. These contours are then typically quantified using a metric such as CD at a user-defined cutting line. Thus, images of device structures are typically compared and quantified using a metric such as the inter-edge distance (CD) measured on the extracted contours or a simple pixel difference between images.

[0098]

[0119] In one embodiment, one or more steps of processes 300, 400, 500, and / or 600 can be implemented as instructions (e.g., program code) in a processor of a computer system (e.g., process 104 of computer system 100). In one embodiment, to increase computational efficiency, the steps may be distributed across multiple processors (e.g., parallel computing). In one embodiment, a computer program product including a non-temporary computer-readable medium has instructions stored on the non-temporary computer-readable medium, and when executed by a computer hardware system, the instructions implement the methods described herein.

[0099]

[0120] According to this disclosure, the disclosed combinations and subcombinations constitute separate embodiments. For example, the first combination includes determining a deblurring model based on depth data related to a design pattern. A subcombination may include determining a deblurred image using the deblurring model. In another combination, the deblurred image can be used in an inspection process to determine OPC or SMO based on distributed data generated by the model. In yet another example, the combination includes determining process adjustments to a lithography process, a resist process, or an etching process based on inspection data based on the deblurred image in order to improve the yield of a patterning process.

[0100]

[0121] Figure 15 is a block diagram of a computer system 100 that can assist in the implementation of a method, flow, or apparatus disclosed herein. The computer system 100 includes a bus 102 or other communication mechanism for communicating information and a processor 104 (or a plurality of processors 104 and 105) coupled to the bus 102 for processing information. The computer system 100 also includes main memory 106 coupled to the bus 102 for storing information and instructions executed by the processor 104, such as random access memory (RAM) or other dynamic storage device. The main memory 106 may also be used to store temporary variables or other intermediate information during the execution of instructions executed by the processor 104. The computer system 100 further includes 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.

[0101]

[0122] The computer system 100 may be coupled via bus 102 to a display 112, such as a cathode ray tube (CRT), flat panel, or touch panel display, for displaying information to the computer user. An input device 114, including alphanumeric and other keys, is coupled to bus 102 to communicate information and command selections to the processor 104. Another type of user input device is a cursor control unit 116, such as a mouse, trackball, or cursor directional keys, for communicating directional information and command selections to the processor 104 and for controlling cursor movement on the display 112. This input device generally has two degrees of freedom (a first axis (e.g., x) and a second axis (e.g., y)) that allow the device to be positioned in a plane. A touch panel (screen) display may be used as an input device.

[0102]

[0123] According to one embodiment, a portion of one or more methods described herein may be performed by a computer system 100 in response to a 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 a storage device 110. The execution of the sequence of instructions contained in main memory 106 causes the processor 104 to perform the process steps described herein. One or more processors in a multiprocessing configuration may be used to execute the sequence of instructions contained in main memory 106. In one alternative embodiment, hardwired circuitry may be used instead of, or together with, software instructions. Thus, the description herein is not limited to any particular combination of hardware circuitry and software.

[0103]

[0124] As used herein, the term “computer-readable medium” refers to any medium involved in providing instructions to the processor 104 for execution. Such mediums can take many forms, but are not limited to non-volatile media, volatile media, and transmission media. Non-volatile media include, for example, optical or magnetic disks such as storage device 110. Volatile media include dynamic memory such as main memory 106. Transmission media include coaxial cables, copper wires, and optical fibers (including wires including bus 102). Transmission media can also take the form of sound waves or light waves, such as those 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, and other magnetic media, CD-ROMs, DVDs, and other optical media, punch cards, paper tapes, and other physical media having perforation patterns, RAM, PROMs, and EPROMs, FLASH-EPROMs, and other memory chips or cartridges, carrier waves as described below, or other media that can be read by a computer.

[0104]

[0125] 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, the instructions may initially reside on a magnetic disk of a remote computer. The remote computer can load the instructions into its dynamic memory and send them over a telephone line using a modem. A modem local to computer system 100 can receive data over the telephone line and convert the data into an infrared signal using an infrared transmitter. An infrared detector coupled to bus 102 can receive the data carried by the infrared signal and load that data onto bus 102. Bus 102 transports the data to main memory 106, from which the processor 104 reads and executes the instructions. Instructions received by main memory 106 may optionally be stored in a storage device 110 before or after execution by the processor 104.

[0105]

[0126] The computer system 100 may also include a communication interface 118 coupled to the bus 102. The communication interface 118 also provides bidirectional data communication coupled to a network link 120 connected to a local network 122. For example, the communication interface 118 may be an ISDN (Integrated Services Digital Network) card or modem that provides data communication connectivity to a corresponding type of telephone line. Alternatively, the communication interface 118 may be a local area network (LAN) card that provides data communication connectivity to a compatible LAN. A wireless link may also be implemented. In such an implementation, the communication interface 118 transmits and receives electrical, electromagnetic, or optical signals that carry digital data streams representing various types of information.

[0106]

[0127] The network link 120 typically provides data communication to other data devices through one or more networks. For example, the network link 120 can provide connection to data equipment operated by a host computer 124 or an Internet service provider (ISP) 126 through a local network 122. The ISP 126 then provides data communication services via the World Wide Packet Data Network (now commonly referred to as the "Internet" 128). Both the local network 122 and the Internet 128 use electrical, electromagnetic, or optical signals to carry digital data streams. Signals across various networks, and signals on the network link 120 and through the communication interface 118, carrying digital data to and from the computer system 100, are examples of carrier wave forms that carry information.

[0107]

[0128] Computer system 100 can send messages and receive data, including program code, through one or more networks, network links 120, and communication interfaces 118. In the Internet example, server 130 may send request code for an application program through the Internet 128, ISP 126, local network 122, and communication interfaces 118. Such a downloaded application may provide all or part of the methods described herein. The received code may be executed by processor 104 upon receipt and / or stored in storage device 110 or other non-volatile storage for later execution. In this way, computer system 100 may obtain application code in carrier form.

[0108]

[0129] Figure 16 schematically illustrates an exemplary lithography projection apparatus that can be used in combination with the techniques described herein. This apparatus includes: - Illumination system IL for adjusting radiation beam B. In this particular case, the illumination system also includes radiation source SO; - A first object table (e.g., a patterning device table) MT, which includes a patterning device holder for holding a patterning device MA (e.g., a reticle) and is connected to a first positioner for precisely positioning the patterning device relative to an item PS; - A second object table (substrate table) WT comprising a substrate holder for holding a substrate W (e.g., a resist-coated silicon wafer) and connected to a second positioner for precisely positioning the substrate relative to an item PS; - A projection system ("lens") PS (e.g., a refractive, reflective, or reflective-refracting optical system) that images the irradiated portion of the patterning device MA onto the target portion C of the substrate W (e.g., including one or more dies).

[0109]

[0130] As described herein, the apparatus is transmissive (i.e., has a transmissive patterning device). However, it may generally be reflective (having a reflective patterning device), for example. The apparatus may use a different type of patterning device than conventional masks, examples of which include a programmable mirror array or an LCD matrix.

[0110]

[0131] The source SO (e.g., a mercury lamp or excimer laser, LPP (laser-generated plasma), or EUV source) generates a radiant beam. This beam is supplied to the illumination system (illuminator) IL either directly or after passing through a regulating means such as a beam expander Ex. The illuminator IL may include regulating means AD for setting the outer and / or inner radial ranges of the beam's intensity distribution (generally referred to as σ-outer and σ-inner, respectively). Furthermore, it generally includes various other components such as an integrator IN and a capacitor CO. In this way, the beam B that strikes the patterning device MA has the desired uniformity and intensity distribution in cross-section.

[0111]

[0132] Regarding Figure 12, it should be noted that the source SO may be located within the housing of the lithography projection apparatus (in most cases, when the source SO is, for example, a mercury lamp), or it may be located away from the lithography projection apparatus, with the emitted beam it generates being guided into the apparatus (for example, using appropriate guide mirrors). This latter scenario is often the case when the source SO is an excimer laser (e.g., based on KrF, ArF, or F2 lathing).

[0112]

[0133] Next, beam PB intersects with the patterning device MA held on the patterning device table MT. After traversing the patterning device MA, beam B passes through lens PL, which focuses beam B onto the target portion C of the substrate W. Using a second positioning means (and interferometric measurement means IF), the substrate table WT can be precisely moved to position, for example, a different target portion C within the path of beam PB. Similarly, for example, after or during a machine search of the patterning device MA from the patterning device library, the patterning device MA can be precisely positioned relative to the path of beam B using the first positioning means. In general, the movement of the object tables MT and WT is achieved using long-stroke modules (coarse positioning) and short-stroke modules (fine positioning), which are not explicitly shown in Figure 16. However, in the case of a stepper (as opposed to a step-and-scan tool), the patterning device table MT may be connected to or fixed only to short-stroke actuators.

[0113]

[0134] The drawn tool can be used in two different modes: - In step mode, the patterning device table MT remains essentially stationary, and the entire patterning device image is projected onto the target portion C in a single pass (i.e., a single "flash"). The substrate table WT is then shifted in the x and / or y directions so that different target portions C can be illuminated by the beam PB; - In scan mode, essentially the same scenario applies, except that a given target portion C is not exposed in a single "flash." Instead, the patterning device table MT is movable at velocity v in a given direction (the so-called "scan direction," e.g., the y-direction) so that the projection beam B can scan over the patterning device image. In parallel, the substrate table WT is simultaneously moved at velocity V=Mv (where M is the magnification of the lens PL (generally M=1 / 4 or 1 / 5)) in the same or opposite direction. In this way, a relatively large target portion C can be exposed without compromising resolution.

[0114]

[0135] Figure 17 schematically shows another exemplary lithography projection apparatus LA that can be used in conjunction with the techniques described herein.

[0115]

[0136] The lithography projection system LA includes the following: - Source collector module SO - Illumination system (illuminator) IL configured to adjust radiation beam B (e.g., EUV radiation) - A support structure (e.g., a patterning device table) MT connected to a first positioner PM, which is constructed to support a patterning device (e.g., a mask or reticle) MA and configured to precisely position the patterning device. - A substrate table (e.g., wafer table) WT connected to a second positioner PW, which is constructed to hold a substrate (e.g., a resist-coated wafer) W and configured to precisely position the substrate, and - A projection system (e.g., a reflective projection system) PS configured to project a pattern applied to a radiant beam B by a patterning device MA onto a target portion C of a substrate W (e.g., including one or more dies).

[0116]

[0137] As depicted here, the apparatus LA is reflective (e.g., using a reflective patterning device). Note that since most materials are absorbent in the EUV wavelength range, the patterning device may have a multilayer reflector, for example, a multi-stack of molybdenum and silicon. In one example, the multi-stack reflector has 40 layers of molybdenum and silicon, with each layer having a thickness of one-quarter of a wavelength. Even smaller wavelengths can be produced using X-ray lithography. Since most materials are absorbent at EUV and X-ray wavelengths, a thin piece of patterned absorbent material on the patterning device topography (e.g., a TaN absorber on a multilayer reflector) defines where features are printed (positive resist) or not printed (negative resist).

[0117]

[0138] Referring to Figure 17, the illuminator IL receives an extreme ultraviolet (EUV) radiation beam from the source collector module SO. Methods for generating EUV radiation include, but are not limited to, converting a material into a plasma state having at least one element (e.g., xenon, lithium, or tin) with one or more emission lines in the EUV range. In one such method, often called laser-generated plasma ("LPP"), the plasma can be generated by irradiating a fuel, such as droplets, streams, or clusters of material having a line-emitting element, with a laser beam. The source collector module SO may also be part of an EUV radiation system including a laser (not shown in Figure 17) that provides the laser beam for exciting the fuel. The resulting plasma emits output radiation (e.g., EUV radiation), which is collected using a radiation collector located in the source collector module. The laser and source collector module may be separate entities, for example, if a CO2 laser is used to provide the laser beam for fuel excitation.

[0118]

[0139] In such cases, the laser is not considered to form part of the lithography apparatus, and the emitted beam is delivered from the laser to the source collector module using a beam delivery system, for example, including appropriate guide mirrors and / or beam expanders. In other cases, for example, if the source is a discharge-generated plasma EUV generator, often called a DPP source, the source may be an integrated part of the source collector module.

[0119]

[0140] An illuminator (IL) may include adjusters for adjusting the angular intensity distribution of the radiated beam. Generally, at least the outer and / or inner radial ranges of the intensity distribution at the pupil surface of the illuminator (commonly referred to as σ-outer and σ-inner, respectively) can be adjusted. Furthermore, an illuminator (IL) may include various other components such as facet fields and pupil mirror devices. Using an illuminator, the radiated beam can be tuned to have desired uniformity and intensity distribution in cross-section.

[0120]

[0141] A radiating beam B is incident on a patterning device (e.g., a mask) MA held on a support structure (e.g., a patterning device table) MT, and is patterned by the patterning device. After being reflected from the patterning device (e.g., a mask) MA, the radiating beam B passes through a projection system PS that focuses the beam onto a target portion C of the substrate W. A second positioner PW and a position sensor PS2 (e.g., an interference device, a linear encoder, or a capacitance sensor) can be used to precisely move the substrate table WT to position, for example, different target portions C within the path of the radiating beam B. Similarly, a first positioner PM and another position sensor PS1 can be used to precisely position the patterning device (e.g., a mask) MA relative to the path of the radiating beam B. The patterning device (e.g., a mask) MA and the substrate W may be aligned using patterning device alignment marks M1, M2 and substrate alignment marks P1, P2.

[0121]

[0142] The depicted device LA can be used in at least one of the following modes:

[0143] 1. In step mode, the support structure (e.g., patterning device table) MT and substrate table WT remain essentially stationary (i.e., single static exposure) while the entire pattern applied to the radiation beam is projected onto the target portion C in a single pass. The substrate table WT is then shifted in the X and / or Y directions so that different target portions C can be exposed.

[0144] 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) while the pattern applied to the radiation beam is projected onto the target portion C. The speed and direction of the substrate table WT relative to the support structure (e.g., patterning device table) MT can be determined by the reduction and image inversion characteristics of the projection system PS.

[0145] 3. In another mode, while the pattern applied to the radiation beam is projected onto the target portion C, the support structure (e.g., patterning device table) MT remains essentially stationary, holding the programmable patterning device, and the substrate table WT is moved or scanned. In this mode, a pulsed radiation source is generally used, and the programmable patterning device is updated as needed after each movement of the substrate table WT or between consecutive radiation pulses during scanning. This operating mode can be readily applied to maskless lithography utilizing programmable patterning devices such as the type of programmable mirror array mentioned above.

[0122]

[0146] Figure 18 shows the apparatus LA in more detail, including the source collector module SO, the illumination system IL, and the projection system PS. The source collector module SO is constructed and positioned so that a vacuum environment can be maintained within the enclosed structure 220 of the source collector module SO. The EUV radiation emission 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, from which the ultra-high temperature plasma 210 is made to emit radiation in the EUV range of the electromagnetic spectrum). The ultra-high temperature plasma 210 is made, for example, by a discharge that produces at least partially ionized plasma. A partial pressure of, for example, 10 Pa of Xe, Li, Sn vapor, or any other suitable gas or vapor may be required for efficient generation of radiation. In one embodiment, a plasma of excited tin (Sn) is provided to generate EUV radiation.

[0123]

[0147] Radiation emitted by the high-temperature plasma 210 is passed from the source chamber 211 into the collector chamber 212 via an optional gas barrier or contaminant trap 230 (sometimes also called a contaminant barrier or foil trap) located within or behind the opening of 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. The contaminant trap or contaminant barrier 230 further described herein includes at least a channel structure, as is known in the art.

[0124]

[0148] The collector chamber 211 may include a radiation collector CO, which may be a so-called oblique incidence collector. The radiation collector CO has an upstream radiation collector side 251 and a downstream radiation collector side 252. Radiation crossing collector CO is reflected by the grating spectral filter 240 and can be focused to a virtual source point IF along the optical axis indicated by the dashed line "O". The virtual source point IF is generally called the intermediate focus, and the source collector module is positioned such that the intermediate focus IF is located at or near the aperture 221 of the closed structure 220. The virtual source point IF is an image of the radiation-emitting plasma 210.

[0125]

[0149] Next, the radiation traverses an illumination system IL which may include faceted field mirror devices 22 and faceted pupil mirror devices 24 arranged in the patterning device MA to provide a desired angular distribution of the radiation beam 21 and a desired uniformity of radiation intensity in the patterning device MA. Upon reflection of the radiation beam 21 in the patterning device MA held by the support structure MT, a patterned beam 26 is formed, and the patterned beam 26 is imaged by the projection system PS onto a substrate W held by the substrate table WT via reflective elements 28, 30.

[0126]

[0150] In general, more elements than those shown in the illustrations may be present in the illumination optical system unit IL and the projection system PS. A grating spectral filter 240 may be optionally present depending on the type of lithography apparatus. Furthermore, more mirrors than those shown in the drawings may be present; for example, 1 to 6 additional reflective elements may be present in the projection system PS than those shown in Figure 18.

[0127]

[0151] The CO collector system shown in Figure 18 is depicted as a nested collector with obliquely incident reflectors 253, 254, and 255, as just one example of a collector (or collector mirror). The obliquely incident reflectors 253, 254, and 255 are arranged axially with respect to the optical axis O, and this type of CO collector system can be used in combination with a discharge-generating plasma source, often referred to as a DPP source.

[0128]

[0152] Alternatively, the source collector module SO may be part of the LPP emission system, as shown in Figure 19. The laser LA is positioned to deposit laser energy onto a fuel such as xenon (Xe), tin (Sn), or lithium (Li) to generate a highly ionized plasma 210 with an electron temperature of several tens of eV. The energy radiation generated during de-excitation and recombination of these ions is emitted from the plasma, collected by the near-normal incident collector system CO, and focused onto the aperture 221 of the closed structure 220.

[0129]

[0153] The concepts disclosed herein can be used to simulate or mathematically model general imaging systems for imaging subwavelength features and may be particularly useful for new imaging techniques capable of generating shorter wavelengths. New techniques already in use include EUV (extreme ultraviolet) and DUV lithography, which can generate wavelengths as short as 193 nm using ArF lasers and even 157 nm using fluorine lasers. EUV lithography can also generate wavelengths in the 20-5 nm range by using a synchrotron to generate photons, or by bombarding a material (solid or plasma) with high-energy electrons.

[0130]

[0154] Embodiments of this disclosure may be further described using the following clauses. 1. A non-temporary computer-readable medium for storing a deblurring model configured to remove blur from a captured image of a patterned substrate, including stored instructions, When an instruction is executed by one or more processors, A simulated image of a substrate corresponding to a target pattern is obtained via a simulator that uses a target pattern from which a pattern on the substrate is derived, wherein the target pattern includes a first target feature formed on a first layer on the substrate and a second target feature formed on a second layer on the substrate, the second layer being located below the first layer on the substrate. Determining edge extent data for features on the substrate corresponding to the first and second target features of a target pattern, based on depth data associated with multiple layers of the substrate, wherein the depth data characterizes the blurring of the edges of the features on the substrate as a function of the depth of each feature from the top layer of the substrate. The process involves using simulated images and edge range data of the substrate as training data to adjust the parameters of the basic model and generate a deblurring model, wherein the deblurring model generates a deblurred image of the captured image of the patterned substrate using edge range data associated with the captured image. A non-temporary computer-readable medium that produces an action including [specific action]. 2. The target pattern is the medium described in Clause 1, including the geometric data associated with the first target feature and the second target feature. 3. Geometric data in the medium described in Clause 2, including the desired shapes of the first target feature and the second target feature within the target pattern, and the target positions of the edges of the first target feature and the second target feature. 4. Depth data is The first depth of the first layer located vertically downward from the top layer, and the second depth of the second layer located vertically downward from the top layer of the substrate, Material data associated with the first and second layers of the substrate, or Diffraction behavior associated with the first and second features on the substrate corresponding to the first and second target features of the target pattern, respectively. A medium described in any one of the clauses 1 to 3, including at least one of the following. 5. Edge range data is a medium specified in any one of clauses 1 to 4, including the range of edge locations on the substrate corresponding to each feature in the target pattern. 6. Determining edge range data is a medium described in any one of Clauses 1 to 5, which includes running a model configured to calculate the edge changes of features on the substrate corresponding to each feature of the target pattern. 7. The edge extent data is represented as an image of the target pattern complemented by the edge extent data of each feature printed on the substrate, in any medium described in any one of Clauses 1 to 6. 8. Obtaining a simulated image is Extracting noise from the captured image of a patterned circuit board, Adding noise to the simulated image, The media described in any one of the clauses 1 to 7, including, further. 9. The deblurring model is a machine learning model, provided it is one of the media described in any of clauses 1 to 8. 10. The deblurring model is a deep convolutional network, and the model parameters include the weights and biases of one or more layers of the deep convolutional network, as described in any one of clauses 1 to 9. 11. The blur removal model is: A feature vector containing values ​​that represent the features of the target pattern, A vector of interest containing values ​​related to the depth associated with a feature printed on a substrate, configured to be computed with a feature vector, A neural network including any one of the media described in any one of clauses 1 to 10. 12. The vector of interest is a medium as described in Clause 11, with a value in the range of 0 to 1, or a value of 0 or 1. 13. The machine learning model is configured to multiply the focus vector by the feature vector such that depth-related weights are assigned by the focus vector to the edges of specific features in the feature vector, as described in Clause 12. 14. The medium described in Clause 13, wherein the first target feature associated with the first layer is multiplied by a higher attention value compared to the attention value multiplied by the second target feature associated with the second layer. 15. A simulator is a medium described in any one of Clauses 1 to 14, which includes a model that is a function of the physical properties of a substrate on which a target pattern is printed, and which generates a simulated image, thereby enabling the determination of feature properties in each layer of the substrate. 16. The physical properties of the substrate include at least one of the following: the material of a particular layer, the thickness of a particular layer, the resist process parameters, or the etching process parameters, as described in Clause 15. 17. Obtaining a simulated image is the medium described in Clause 16, which includes simulating a model that generates a simulated image through a Monte Carlo simulation process. 18. Obtaining a simulated image involves simulating a double Gaussian model configured to generate a simulated image based on depth data, as described in Clause 16. 19. Capturing an image of a patterned multilayer substrate using a given target pattern via a capture device, Determining edge range data for the features on the substrate corresponding to each feature of a given target pattern, The edge range data and captured image are input into the deblurring model to generate a deblurred image of the captured image, The media described in any one of the clauses 1 to 18, including further media. 20. The captured image is a scanning electron beam (SEM) image obtained by a high-energy setting used to capture an image of a patterned multilayer substrate, as described in Clause 19. 21. The target pattern is a polygon-based hierarchical data format in any of the media described in any one of Clauses 1 to 20. 22. Polygon-based data formats include the GDS format and the media described in Clause 21. 23. A non-temporary computer-readable medium for removing blur from images obtained from a scanning electron microscope (SEM) by using data relating to the layer depth of a patterned substrate, including stored instructions, When an instruction is executed by one or more processors, Receiving a captured image of a patterned substrate, This involves inputting the captured image into the deblurring model, and the deblurring model is Obtaining a simulated image of a substrate corresponding to a target pattern via a simulator that uses a target pattern from which a pattern on the substrate is derived, wherein the target pattern includes a first target feature formed on a first layer on the substrate and a second target feature formed on a second layer on the substrate, the second layer being located below the first layer on the substrate. Determining edge extent data for features on the substrate corresponding to the first and second target features of a target pattern, based on depth data associated with multiple layers of the substrate, wherein the depth data characterizes the blurring of the edges of the features on the substrate as a function of the depth of each feature from the top layer of the substrate. The process involves using simulated images and edge range data of the substrate as training data to adjust the parameters of the basic model and generate a deblurring model. Being trained by, Using the captured image and the edge range data associated with the features of the patterned substrate, the output is received from the deblurring model. To generate a captured image with the blur removed from the captured image on the user interface for display, A non-temporary computer-readable medium that produces an action including [specific action]. 24. The target pattern is the medium described in Clause 23, which includes the geometric data associated with the first target feature and the second target feature. 25. Geometric data includes the desired shapes of the first target feature and the second target feature, and the target positions of the edges of the first target feature and the second target feature, respectively, as described in the medium of Clause 24. 26. Geometric data, The first depth of the first layer, measured vertically downward from the top layer, and the second depth of the second layer, measured vertically downward from the top layer of the substrate. Material data associated with the first and second layers of the substrate, or Diffraction behavior associated with the first and second features on the substrate corresponding to the first and second target features of the target pattern, respectively. A medium described in any one of the clauses 23 to 25, including at least one of the following. 27. Edge range data includes the range of edge locations of features on the substrate corresponding to each feature in the target pattern, in the medium specified in any one of clauses 23 to 26. 28. Determining edge range data includes running a model configured to calculate the edge changes of features on the substrate corresponding to each feature of the target pattern, as described in any one of the media in any of the clauses 23 to 27. 29. Edge extent data is represented as an image of the target pattern complemented by the edge extent data of each feature of the target pattern, in any of the media described in any one of clauses 23 to 28. 30. The deblurring model is a machine learning model, as specified in any one of clauses 23-29. 31. The deblurring model is a deep convolutional network, and the model parameters include the weights and biases of one or more layers of the deep convolutional network, as described in any one of the clauses 23 to 30. 32. A simulator is a medium as described in any one of Clauses 23 to 31, which includes a model that is a function of the physical properties of a substrate on which a target pattern is printed, and which generates a simulated image, thereby enabling the determination of feature properties in each layer of the substrate. 33. The captured image is a scanning electron beam (SEM) image obtained by a high-energy setting used to capture an image of a patterned multilayer substrate, as described in any one of clauses 23 to 32. 34. A non-temporary computer-readable medium for removing blur from a captured image of a patterned substrate, including stored instructions, When an instruction is executed by one or more processors, The method involves inputting a capture image and edge range data of a patterned substrate associated with a target pattern into a deblurring model, wherein the deblurring model is trained based on the edge range data associated with the target pattern features at a specific depth. By running a deblurring model, the blur of the captured image is removed, A non-temporary computer-readable medium that produces an action including [specific action]. 35. Edge extent data for features on the substrate corresponding to features of the target pattern is determined based on depth data associated with the target pattern and the substrate, as described in Clause 34. 36. Depth data is The first depth of the first layer, measured vertically downward from the top layer, and the second depth of the second layer, measured vertically downward from the top layer of the substrate. Material data associated with the first and second layers of the substrate, or Diffraction behavior associated with the first and second features on the substrate corresponding to the first and second target features of the target pattern, respectively. The media described in Clause 35, including at least one of the following. 37. Edge range data includes the range of edge locations for features on the substrate corresponding to each feature in the target pattern, in the medium described in any one of clauses 34 to 36. 38. Determining edge range data includes running a model configured to calculate the edge changes of features on the substrate corresponding to each feature of the target pattern, as described in Clause 34. 39. Edge extent data is represented as an image of the target pattern complemented by the edge extent data corresponding to each feature of the target pattern, in any of the media described in any one of clauses 34 to 38. 40. A method for removing blur from a captured image of a patterned substrate, Identifying features in the captured image based on target pattern and depth data associated with multiple layers of a patterned substrate, By removing blur from each feature based on the target pattern and depth data, the blur of the captured image is removed, Methods that include... 41. Depth data is, The first depth of the first layer from the top layer of the patterned substrate, and the second depth of the second layer from the top layer, Material data for the first and second layers of the patterned substrate, or, Diffraction behavior associated with the first and second features on the substrate corresponding to the first and second target features of the target pattern, respectively. The method described in Clause 40, which includes at least one of the following. 42. The method according to Clause 41, wherein identifying features in a captured image includes determining edge extent data for features on a patterned substrate based on depth data associated with multiple layers of the patterned substrate. 43. The method according to Clause 42, wherein the edge range data includes the range of edge locations of features on the substrate corresponding to each feature in the target pattern. 44. The method of Clause 43, wherein determining edge range data includes running a model configured to calculate the edge changes of features on the substrate corresponding to each feature of the target pattern. 45. The method described in any one of clauses 42 to 44, wherein the edge extent data is represented as an image of the target pattern complemented by the edge extent data corresponding to each feature of the target pattern. 46. ​​A method for generating a blur removal model and removing blur from a captured image of a patterned substrate, Obtaining a simulated image of a substrate corresponding to a target pattern via a simulator that uses a target pattern from which a pattern on the substrate is derived, wherein the target pattern includes a first target feature formed on a first layer on the substrate and a second target feature formed on a second layer on the substrate, the second layer being located below the first layer on the substrate. Determining edge extent data for features on the substrate corresponding to the first and second target features of a target pattern, based on depth data associated with multiple layers of the substrate, wherein the depth data characterizes the blurring of the edges of the features on the substrate as a function of the depth of each feature from the top layer of the substrate. The process involves using simulated images and edge range data of the substrate as training data to adjust the parameters of the basic model and generate a deblurring model, wherein the deblurring model generates a deblurred image of the captured image of the patterned substrate using edge range data associated with the captured image. Methods that include... 47. The method according to Clause 46, wherein the target pattern includes geometric data associated with a first target feature and a second target feature. 48. The method according to Clause 47, wherein the geometric data includes the desired shapes of a first target feature and a second target feature within the target pattern, and the target positions of the edges of the first target feature and the second target feature. 49. Depth data is, The first depth of the first layer located vertically downward from the top layer, and the second depth of the second layer located vertically downward from the top layer of the substrate, Material data associated with the first and second layers of the substrate, or Diffraction behavior associated with the first and second features on the substrate corresponding to the first and second target features of the target pattern, respectively. The method described in any one of the clauses 46 to 48, including at least one of the following: 50. The method described in any one of the clauses 46 to 49, wherein edge range data includes the range of edge locations for features on the substrate corresponding to each feature in the target pattern. 51. Determining edge range data is the method described in any one of the clauses 46 to 50, which includes running a model configured to calculate the edge changes of features on the substrate corresponding to each feature of the target pattern. 52. The method described in any one of clauses 46 to 51, wherein the edge extent data is represented as an image of the target pattern complemented by the edge extent data corresponding to each feature of the target pattern. 53. Obtaining a simulated image is Extracting noise from the captured image of a patterned circuit board, Adding noise to the simulated image, The method described in any one of the clauses 46 to 52, further including the method described in any one of the clauses 46 to 52. 54. The deblurring model is a machine learning model, as described in any one of clauses 46 to 53. 55. The deblurring model is a deep convolutional network, and the model parameters include the weights and biases of one or more layers of the deep convolutional network, as described in any one of the clauses 46 to 54. 56. The blur removal model is, A feature vector containing values ​​that represent the features of the target pattern, A vector of interest containing values ​​related to the depth associated with a feature printed on a substrate, configured to be computed with a feature vector, A neural network including the method described in any one of clauses 46 to 55. 57. The vector of interest is a value in the range of 0 to 1, or a value of 0 or 1, as described in Clause 56. 58. The method according to Clause 57, wherein the machine learning model is configured to multiply the attention vector by the feature vector such that depth-related weights are assigned to the edges of specific features in the feature vector by the attention vector. 59. The method according to clause 58, wherein a first target feature associated with a first layer of the substrate is multiplied by a higher attention value compared to the attention value multiplied by a second target feature associated with a second layer of the substrate. 60. The method according to any one of the clauses 46 to 59, comprising a model which is a function of the physical properties of a substrate on which a target pattern is printed, and which generates a simulated image, thereby enabling the determination of feature properties in each layer of the substrate. 61. The method according to Clause 60, wherein the physical properties of the substrate include at least one of the materials of a particular layer, the thickness of a particular layer, resist process parameters, or etching process parameters. 62. Obtaining a simulated image is the method of Clause 61, which includes simulating a model that generates a simulated image through a Monte Carlo simulation process. 63. Obtaining a simulated image is the method of Clause 62, which includes simulating a double Gaussian model configured to generate a simulated image based on depth data. 64. Capturing an image of a patterned multilayer substrate using a given target pattern via a capture device, Determining edge range data for the features on the substrate corresponding to each feature of a given target pattern, The edge range data and captured image are input into the deblurring model to generate a deblurred image of the captured image, The method described in any one of the clauses 46 to 63, further including the method described in any one of the clauses 46 to 63. 65. The method according to clause 64, wherein the captured image is a scanning electron beam (SEM) image obtained by a high-energy setting used to capture an image of a patterned multilayer substrate. 66. The target pattern is a polygon-based hierarchical data format, as described in any one of the provisions 46 to 65. 67. Polygon-based data formats include the GDS format, as described in Clause 66. 68. A method for removing blur from a captured image of a patterned substrate, The method involves inputting a capture image and edge range data of a patterned substrate associated with a target pattern into a deblurring model, wherein the deblurring model is trained based on the edge range data associated with the target pattern features at a specific depth. By running a deblurring model, the blur of the captured image is removed, Methods that include... 69. The method according to Clause 68, wherein the edge extent data for features on the patterned substrate corresponding to features of the target pattern is determined based on the depth data associated with the target pattern and the substrate. 70. Depth data is, The first depth of the first layer located vertically downward from the top layer, and the second depth of the second layer located vertically downward from the top layer of the substrate, Material data associated with the first and second layers of the substrate, or Diffraction behavior associated with the first and second features on the substrate corresponding to the first and second target features of the target pattern, respectively. The method described in Article 69, which includes at least one of the following. 71. The method described in any one of the clauses 68 to 70, wherein the edge range data includes the range of edge locations for features on the substrate corresponding to each feature in the target pattern. 72. The method of Clause 68, wherein determining edge range data includes running a model configured to calculate the edge variation of a feature on the substrate corresponding to each feature of the target pattern. 73. The method described in any one of clauses 68 to 72, wherein the edge extent data is represented as an image of the target pattern complemented by the edge extent data corresponding to each feature of the target pattern. 74. A system for removing blur from the captured image of a patterned substrate, An electron beam optical system configured to capture an image of a patterned substrate patterned based on a target pattern, A deblurring model comprising one or more processors configured to deblur the captured image by inputting and executing a deblurring model, wherein the deblurring model is trained on edge range data associated with features of the target pattern at a certain depth, and the deblurring model is trained on edge range data associated with features of the target pattern at a certain depth, and the deblurring model is executed. A system that includes this. 75. The system described in Clause 74, in which the edge extent data for features on the patterned substrate corresponding to the features of the target pattern is determined based on the depth data associated with the target pattern and the substrate. 76. Depth data is, The first depth of the first layer located vertically downward from the top layer, and the second depth of the second layer located vertically downward from the top layer of the substrate, Material data associated with the first and second layers of the substrate, or Diffraction behavior associated with the first and second features on the substrate corresponding to the first and second target features of the target pattern, respectively. A system as described in Clause 75, including at least one of the following. 77. Edge range data includes the range of edge locations for features on the substrate corresponding to each feature in the target pattern, as described in any one of clauses 74 to 76. 78. Determining edge range data is a system as described in Clause 77, which includes running a model configured to calculate the edge changes of features on the substrate corresponding to each feature of the target pattern. 79. The system described in any one of clauses 74-78, in which the edge extent data is represented as an image of the target pattern complemented by the edge extent data corresponding to each feature of the target pattern.

[0131]

[0155] The concepts disclosed herein may be used for imaging on substrates such as silicon wafers, but it will be understood that the disclosed concepts may be used in conjunction with any type of lithography imaging system, such as those used for imaging on substrates other than silicon wafers.

[0132]

[0156] When used herein, unless otherwise specified, the term “or” encompasses all possible combinations unless it is impossible to achieve. For example, if it is stated that a database may contain A or B, then unless otherwise specified or impossible to achieve, the database may contain A or B, or A and B. As a second example, if it is stated that a database may contain A, B, or C, then unless otherwise specified or impossible to achieve, the database may contain A or B, or C, or A and B, or A and C, or B and C, or A and B and C.

[0133]

[0157] The above description is intended to be illustrative, not restrictive. Therefore, it will be apparent to those skilled in the art that modifications can be made as described without departing from the claims presented below.

Claims

1. A non-temporary computer-readable medium for storing a deblurring model configured to remove blur from a captured image of a patterned substrate, including stored instructions, When the aforementioned instruction is executed by one or more processors, Obtaining a simulated image of the substrate corresponding to the target pattern via a simulator that uses a target pattern from which a pattern on the substrate is derived, wherein the target pattern includes a first target feature formed on a first layer on the substrate and a second target feature formed on a second layer on the substrate, the second layer being located below the first layer on the substrate. Determining edge range data for features on the substrate corresponding to the first and second target features of the target pattern, based on depth data associated with multiple layers of the substrate, wherein the depth data characterizes the blurring of the edges of the features on the substrate as a function of the depth of each feature from the top layer of the substrate. The process involves using the simulated image and edge range data of the substrate as training data to adjust the parameters of the basic model and generate the deblurring model, wherein the deblurring model generates a deblurred image of the captured image of the patterned substrate using the edge range data associated with the captured image. A non-temporary computer-readable medium that produces an action including [specific action].

2. The medium according to claim 1, wherein the target pattern includes geometric data associated with the first target feature and the second target feature.

3. The medium according to claim 2, wherein the geometric data includes, respectively, the desired shapes of the first target feature and the second target feature within the target pattern, and the target positions of the edges of the first target feature and the second target feature.

4. The aforementioned depth data is The first depth of the first layer located vertically downward from the uppermost layer, and the second depth of the second layer located vertically downward from the uppermost layer of the substrate, Material data associated with the first layer and the second layer of the substrate, or Diffraction behavior associated with the first and second features on the substrate corresponding to the first and second target features of the target pattern, respectively. The medium according to claim 1, comprising at least one of the following.

5. The medium according to claim 1, wherein the edge range data includes the range of edge positions on the substrate corresponding to each feature in the target pattern.

6. Determining the aforementioned edge range data means that The medium according to claim 1, comprising running a model configured to calculate edge changes of features on the substrate corresponding to each feature of the target pattern.

7. The medium according to claim 1, wherein the edge range data is represented as an image of the target pattern complemented by the edge range data of each feature printed on the substrate.

8. Obtaining the aforementioned simulated image means Extracting noise from the captured image of a patterned circuit board, Adding the noise to the simulated image, The medium according to claim 1, further comprising:

9. The medium according to claim 1, wherein the blur removal model is a machine learning model.

10. The medium according to claim 1, wherein the de-blurring model is a deep convolutional network, and the model parameters include the weights and biases of one or more layers of the deep convolutional network.

11. The aforementioned blur removal model is A feature vector containing values ​​that represent the features of the target pattern, A focus vector, which includes a value relating to the depth associated with the feature printed on the substrate, and is configured to be calculated with the feature vector, The medium according to claim 1, which is a neural network including

12. The medium according to claim 11, wherein the vector of interest has a value in the range of 0 to 1, or a value of 0 or 1.

13. The medium according to claim 12, wherein the machine learning model is configured to multiply the attention vector by the feature vector such that depth-related weights are assigned by the attention vector to the edges of specific features in the feature vector.

14. The medium according to claim 13, wherein the first target feature associated with the first layer is multiplied by a higher attention value compared to the attention value multiplied by the second target feature associated with the second layer.

15. A method for removing blur from a captured image of a patterned substrate, Identifying features in the captured image based on target patterns and depth data associated with multiple layers of the patterned substrate, The blurring of the captured image is removed by removing the blurring of each of the features based on the target pattern and the depth data, Methods that include...

Images