Metrology solution for complex structures of interest

Abstract

Complex structures in semiconductor devices, such as gate all around (GAA) field effect transistors or high aspect ratio (HAR) channel hole etches, are measured using a combination of physical modeling and machine learning modeling. Metrology signals collected at different manufacturing process steps (e.g., pre-processing and post-processing steps of a structure of interest (SOI)) may be used. The measurement signal obtained at the pre-processing step is used to determine a first parameter of the SOI, which can be fed forward and used to generate a physical model of the SOI at the post-processing step, for example using physical modeling and machine learning. Physical modeling and machine learning are used to determine a second parameter of the SOI at the post-processing step, and the second parameter may be fed back and used to generate the physical model of the SOI at the post-processing step using a post-processing signal and to determine other parameters.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to and the benefit of U.S. Provisional Application No. 63 / 355,053, filed on June 23, 2022, entitled “METROLOGY SOLUTIONS FOR GATE-ALL-ROUNDING TRANSISTORS,” U.S. Provisional Application No. 63 / 498,475, filed on April 26, 2023, entitled “MULTIPLE SOURCES OF SIGNALS FOR HYBRID METROLOGY USING PHYSICAL MODELING AND MACHINE LEARNING,” and U.S. Non-Provisional Application No. 18 / 339,971, filed on June 22, 2023, entitled “METROLOGY SOLUTIONS FOR COMPLEX STRUCTURES OF INTEREST,” all of which are assigned to the assignee of this application and are incorporated herein by reference in their entirety. Technical Field

[0003] The subject matter described herein relates generally to metrology, and more particularly to modeling and measuring structures using multiple data sources and a combination of physical modeling and machine learning. Background Art

[0004] The semiconductor and other similar industries often use metrology such as optical metrology or X-ray metrology to perform non-contact evaluation of samples during processing. For example, with optical metrology, the sample being measured is illuminated with light, for example, at a single wavelength or multiple wavelengths. After the light interacts with the sample, the resulting light is detected and analyzed to determine one or more characteristics of the sample.

[0005] The analysis typically includes modeling the structure under test. The model can be generated based on the physical properties of the structure (such as the material and nominal parameters of the structure, such as film thickness, optical properties of the material, line width and interval width, etc.), and is therefore sometimes referred to as a physical model. One or more parameters of the model can be changed, and the predicted data for each parameter change can be calculated based on the model, for example, using Rigorous Coupled Wave Analysis (RCWA) or other similar techniques. For example, in a nonlinear regression process, the measured data can be compared with the predicted data for each parameter change until a good fit is achieved between the predicted data and the measured data, at which point the fitted parameters are considered to be accurate representations of the parameters of the structure under test. However, modeling can be time-consuming and computationally intensive, and is expensive, especially for small complex features. Summary of the invention

[0006] A combination of physical modeling and machine learning modeling is used to measure complex structures in semiconductor devices, such as gate-all-around (GAA) field effect transistors or high-aspect ratio (HAR) channel hole etching. In addition, metrology signals are collected in different manufacturing process steps, for example, in pre-processing steps and post-processing steps for structures of interest (SOI). The measurement signal obtained in the pre-processing step is used to determine a first parameter of the SOI, for example, using physical modeling and machine learning, which can be fed forward and used to generate a physical model of the SOI in the post-processing step to improve accuracy. The second parameter of the SOI of the post-processing step is determined using physical modeling and machine learning, and the second parameter can be fed back and used to generate a physical model of the SOI in the post-processing step to improve sensitivity and break parameter correlation.

[0007] In one specific implementation, a method for measuring multiple parameters of interest from a structure of interest (SOI) includes obtaining a post-processing step measurement signal for an SOI on one or more samples from a metrology device in a post-processing step. The method also includes extracting a post-processing measurement result from a post-processing physical model of the SOI based on the post-processing step measurement signal and at least one of the following: a value of a first parameter of the SOI at a pre-processing step fed forward to the post-processing physical model, a value of a second parameter of the SOI at the post-processing step fed back to the post-processing physical model, and a combination thereof. The method also includes predicting a final value of the second parameter of the SOI at the post-processing step from a trained post-processing machine learning model based on the post-processing measurement result extracted from the post-processing physical model, and providing at least the final value of the second parameter of the SOI.

[0008] In one specific implementation, a computer system configured to measure a plurality of parameters of interest from a structure of interest (SOI) includes at least one processor, wherein the at least one processor is configured to obtain a post-processing step measurement signal for the SOI on one or more samples from a metrology device at a post-processing step. The at least one processor is also configured to extract a post-processing measurement result from a post-processing physical model of the SOI based on the post-processing step measurement signal and at least one of the following: a value of a first parameter of the SOI at a pre-processing step fed forward to the post-processing physical model, a value of a second parameter of the SOI at the post-processing step fed back to the post-processing physical model, and a combination thereof. The at least one processor is also configured to predict a final value of the second parameter of the SOI at the processing step from a trained post-processing machine learning model based on the post-processing measurement result extracted from the post-processing physical model, and provide at least the final value of the second parameter of the SOI.

[0009] In one specific implementation, a system for measuring multiple parameters of interest from a structure of interest (SOI) includes a component for obtaining a post-processing step measurement signal for the SOI on one or more samples from a metrology device at a post-processing step. The system also includes a component for extracting a post-processing measurement result from a post-processing physical model of the SOI based on the post-processing step measurement signal and at least one of the following: a value of a first parameter of the SOI at a pre-processing step fed forward to the post-processing physical model, a value of a second parameter of the SOI at the post-processing step fed back to the post-processing physical model, and a combination thereof. The system also includes a component for predicting a final value of the second parameter of the SOI at the post-processing step from a trained post-processing machine learning model based on the post-processing measurement result extracted from the post-processing physical model, and a component for providing at least the final value of the second parameter of the SOI. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1A Examples of a planar transistor architecture, a fin transistor architecture, and a gate-all-around (GAA) field effect transistor architecture are illustrated.

[0011] Figure 1B An example of a GAA transistor is illustrated.

[0012] Figure 2 Illustrated is a schematic diagram of a metrology apparatus that may be used to characterize a sample as discussed herein.

[0013] Figure 3 A workflow for offline recipe creation according to a first example scenario is illustrated, wherein signals are collected from multiple data sources including different tools and / or sources.

[0014] Figure 4 A workflow for online measurement according to a first example scenario is illustrated, wherein signals are collected from multiple data sources including different tools and / or sources.

[0015] Figure 5 A workflow for offline recipe creation according to a second example scenario is illustrated, where signals are collected from multiple data sources including different manufacturing process steps.

[0016] Figure 6 A workflow for in-line measurement according to a second example scenario is illustrated, where signals are collected from multiple data sources comprising different manufacturing process steps.

[0017] Figure 7 A workflow for offline recipe creation according to a third example scenario is illustrated, where signals are collected from multiple data sources (eg, different manufacturing process steps).

[0018] Figure 8 A workflow for in-line measurement according to a third example scenario is illustrated, where signals are collected from multiple data sources including different manufacturing process steps.

[0019] Figures 9 and 10 A flow chart depicting a method for characterizing a device on a sample based on multiple data sources is illustrated. DETAILED DESCRIPTION

[0020] During the manufacture of semiconductors and similar devices, it is often necessary to monitor the manufacturing process by non-destructively measuring these devices. One type of metrology that can be used to non-destructively measure samples during processing is optical metrology, which can use a single wavelength or multiple wavelengths and can include, for example, ellipsometry, reflectometry, Fourier transform infrared spectroscopy (FTIR), etc. Other types of metrology can also be used, including X-ray metrology, photoacoustic metrology, electron beam (E-beam) metrology, etc.

[0021] Optical metrology (such as thin film metrology and optical critical dimension (OCD) metrology) and other types of metrology sometimes use physical modeling techniques to generate predicted data for a sample, which is compared with the measured data from the sample. Using physical modeling techniques, a sample model including key parameters and non-key parameters is generated. The model can be based on the nominal parameters of the sample and can include one or more variable parameters, such as layer thickness, line width, space width, sidewall angle, material properties, etc., which can vary within a desired range, for example, depending on the process parameters used to manufacture the sample being measured. The model can also include parameters related to the tool set, such as the characteristics of the optical system used by the metrology equipment. The predicted data can be calculated based on the parameters of the physical model (including changes in the variable parameters) and the characteristics of the metrology equipment using analytical or semi-analytical methods (such as effective medium theory (EMT), finite difference time domain (FDTD), transfer matrix method (TMM), Fourier modal method (FMM) / rigorous coupled wave analysis (RCWA), finite element method (FEM), etc.). For example, in a nonlinear regression process, the measured data obtained from a sample by a metrological device are compared with the predicted data for different parameter changes until the best fit is achieved, at which point the values ​​of the fitted parameters are considered to be an accurate representation of the sample parameters.

[0022] Conventionally, modeling requires that preliminary structural information and preliminary material information about the sample are known in order to generate an accurate representative model of the sample, which contains one or more variable parameters. For example, the preliminary structural information and preliminary material information of the sample can contain a physical description of the structure type and the sample, which has nominal values ​​of various parameters, such as layer thickness, line width, interval width, sidewall angle, material properties, etc., and the range in which these parameters can vary. The model may further contain one or more parameters that are immutable, i.e., parameters that are not expected to change significantly in the sample during manufacturing. The variable parameters of the model are adjusted, and prediction data can be generated in real time during the nonlinear regression process, or a library can be generated in advance. Therefore, modeling applies physical constraints in the analysis, and therefore provides a high level of fidelity for the measurement results. However, due to the physical calculations necessary to generate prediction data, modeling has a high computational cost. For example, modeling a complex 3D structure suffers from a slow time to solution (TTS), and due to the difficulty in fitting the data for the complex structure, the modeling accuracy may be reduced.

[0023] Another technique that can be used to generate prediction data for a sample based on measurement data obtained from the sample by a metrology device is machine learning. Machine learning algorithms that can be used for metrology may include, for example, but are not limited to, linear regression, neural networks, deep learning, convolutional neural networks (CNNs), ensemble methods, support vector machines (SVMs), random forests, etc., or a combination of multiple models in sequential and / or parallel modes. Machine learning does not require a physical model of the sample. Instead, reference data (e.g., measurement data obtained by a metrology device from one or more reference samples) and values ​​of structural parameters of interest are obtained, and the reference data is used to generate and train a machine learning model. The machine learning model is automatically trained using reference data and known values ​​of structural parameters to find relevant data features and learn the inherent relationship and connection between input features and output features in order to make decisions and predictions for new data. The benefits of using machine learning are fast solution time (TTS) and minimal demand for computing resources. However, machine learning requires a large amount of reference data, which is expensive and time-consuming to obtain. In the absence of a large amount of reference data, the machine learning model may suffer from overfitting due to the lack of physical constraints.

[0024] As semiconductor devices continue to shrink, metrology budgets become tighter. In addition, complex 3D structures are more frequently adopted to achieve continuous device scaling. Advances in semiconductor technology, such as the use of complex 3D structures, present additional challenges to metrology due to increased modeling complexity and parameter dependencies as well as reduced sensitivity. For example, the signal from a single metrology tool or source may not have sufficient sensitivity to accurately measure the parameters of interest for semiconductor process quality control. Ultimately, there may not be a single metrology tool that can handle all metrology requirements for most advanced semiconductor devices.

[0025] As discussed herein, by using data collected from multiple data sources (e.g., from multiple tool groups and / or process steps) and using additional data related to samples collected from metrology and / or production equipment (e.g., sensor data), computationally efficient data analysis methods can fuse the multiple data sources and produce more accurate and consistent measurements than can be provided by any individual data source. The analysis methods can be flexible to accommodate data of a variety of different natures, while making the most of existing well-developed techniques, such as physical modeling or machine learning, for each type of data source, and synergizing the strengths of the individual metrology techniques.

[0026] As discussed herein, physical modeling and machine learning are combined to analyze multiple data sources for hybrid metrology and ecosystems. The methods described herein generate predictive capabilities through data mining and data fusion from multiple data sources (e.g., multiple metrology tool groups, sample data from multiple process steps, metrology equipment parameters, and production equipment parameters). By way of example, physical models can be used to analyze metrology signals from one or more metrology tools (such as spectroscopic ellipsometers, spectroscopic reflectometers, X-ray metrology, photoacoustic metrology, Fourier transform infrared spectroscopy (FTIR), electron beam metrology, etc.) to extract measurement results of key parameters and non-key parameters of samples in pre-processing steps and post-processing steps. In addition, machine learning models can be constructed and trained to predict the parameters of interest of samples in pre-processing steps and post-processing steps. The post-processing physical model that extracts the post-processing measurement signal can use the predicted parameters of interest from the pre-processing step predicted by the pre-processing physical model or the pre-processing machine learning model through feed-forward. Additionally or alternatively, the predicted parameters of interest from the post-processing step can be fed back to the post-processing physical model or the post-processing machine learning model to determine other parameters of interest.

[0027] The proposed technique can be used to combine and analyze multiple data sources in an efficient and flexible way, thereby synergizing physical modeling and machine learning with controllable computational cost and software and modeling complexity, thus providing the most feasible solution with manageable time to solution (TTS) and improved final results and overall metrology performance. The method is also general and can be applied to the measurement of any device, OCD, thin film or other type of target.

[0028] By way of example, Figure 1ASemiconductor devices 110, 120, and 130 having planar, fin, and all-around gate (GAA) field effect transistor architectures, respectively, are illustrated. The planar transistor architecture used in device 110 uses a gate 112 located on a channel 114 to control the flow of current through the channel between the source and the drain. A voltage applied to the gate generates an electric field (FET field effect transistor) that excludes or allows carriers in the channel, thereby turning the current on or off. The source, channel, and drain are coplanar, generated at the surface of the semiconductor wafer, and the gate is located above the channel. To combat the effects of increased leakage currents that degrade their performance due to size reduction, finFETs are employed, as illustrated in device 120, in which a channel 124 has the shape of a fin, surrounded on three sides by a gate 122. The use of a gate 122 increases the effective area of ​​the gate 122 close to the channel 124. However, limitations have been encountered with finFETs, and other more complex architectures have been employed. For example, the device 130 uses a gate-all-around (GAA) design, in which the gate 132 completely surrounds the channel 134. The GAA transistor device 130 includes multiple vertically stacked nanosheet channels 134 passing through a single gate 132. While the GAA device 130 promises continued improvement in performance, the three-dimensional features and small size greatly increase the complexity of the manufacturing process and require accurate monitoring using non-destructive metrology.

[0029] For example, Figure 1B A more detailed view of a GAA transistor device 150 during fabrication is illustrated, including a cross-sectional view 150A vertically through a silicon (Si) channel 152 between a source and a drain (not shown). The GAA transistor device 150 is illustrated, showing the Si channel 152 being completely surrounded by a gate when a silicon germanium (SiGe) layer 154 and a dummy gate 156 are replaced. Figure 1B Three repetitive SiGe regions having different critical dimensions (CDs), eg, SiGe CD1, SiGe CD2, and SiGe CD3, are illustrated.

[0030] GAA manufacturing process flow is similar to that used to produce Figure 1AThe finFET process of the device 120 shown in FIG. 1 has similarities. The process begins with the creation of, for example, a superlattice, which is a stack of alternating epitaxially deposited silicon and silicon germanium (SiGe) layers. Trenching is etched through the lattice to create a fin-like structure, each fin containing three to four silicon nanosheet layers, which will become the transistor Si channel 152 separated by SiGe layers 154. The silicon layers are alternated with SiGe layers that will be replaced by gate materials. A dummy polysilicon gate 156 is deposited across the nanosheet fin, and the spacer material is conformally deposited on the dummy gate. The source and drain are etched on either side of the gate, cutting through and exposing the ends of the Si channel 152. In a series of important steps, the exposed SiGe layer between the ends of the Si channel 152 is selectively etched to create a cavity for the internal spacer 158, and then the internal spacer is deposited in the cavity. These features are very small, yet their size is considered critical in determining the performance of the device for several reasons. For example, the depth of the cavity and internal spacers determine the length of the gate, the internal spacers protect the subsequently deposited source and drain during layer release when the dummy gate is etched away and replaced with gate material, and the spacers suppress parasitic capacitance between the source / drain and the gate.

[0031] Therefore, accurately monitoring these components in a GAA transistor device, or other similar components in a GAA transistor device or other complex 3D structures, is important during manufacturing but difficult using conventional metrology techniques.

[0032] By way of example, Figure 2 A schematic diagram of a metrology apparatus 200 that may be used to characterize structures on a sample, as described herein, is illustrated. The metrology apparatus 200 may be configured to perform one or more types of measurements of the sample 203, such as, for example, spectroscopic reflectance measurements, spectroscopic ellipsometry measurements (including Miller matrix ellipsometry measurements), spectroscopic scatterometry measurements, overlap scatterometry measurements, interferometry measurements, photoacoustic metrology, electron beam metrology, X-ray metrology, FTIR measurements, etc. The metrology apparatus 200 may include, for example, a first metrology tool 201 and a second metrology tool 270, but may include additional metrology tools, or may be coupled to receive sample data measured by separate metrology tools. It should be understood that the metrology apparatus 200 is illustrated as one example configuration of a metrology apparatus, and other configurations and other metrology apparatus may be used if desired.

[0033] The metrology apparatus 200 includes an oblique incidence metrology tool 201, which includes a light source 210 that generates light 202. For example, the light 202 can be UV visible light having a wavelength, for example, between 200 nm and 1000 nm. The light 202 generated by the light source 210 can include a range of wavelengths, i.e., a continuous range or a plurality of discrete wavelengths, or can be a single wavelength. The metrology apparatus 200 includes focusing optics 220 and 230 that focus and receive the light and direct the light so as to be obliquely incident on the top surface of the sample 203. The optics 220, 230 can be refractive, reflective, or a combination thereof, and can be an objective lens.

[0034] The reflected light may be focused by lens 214 and received by detector 250. Detector 250 may be a conventional charge coupled device (CCD), photodiode array, CMOS, or similar type of detector. If broadband light is used, detector 250 may be, for example, a spectrometer, and detector 250 may, for example, generate a spectral signal as a function of wavelength. A spectrometer may be used to disperse the full spectrum of received light into spectral components across the detector pixel array. One or more polarization elements may be located in the beam path of metrology device 200. For example, metrology device 200 may include one or both (or none) of one or more polarization elements 204 in the beam path before sample 203 and a polarization element (analyzer) 212 in the beam path after sample 203, and may include one or more additional elements 205a and 205b, such as compensators or photoelastic modulators, which may be before, after, or before and after sample 203. By using a spectroscopic ellipsometer using a dual rotating compensator between polarization elements 204 and 212 and the sample, a full Miller matrix may be measured.

[0035] The metrology apparatus 200 may include or may be coupled to additional metrology apparatus. For example, as illustrated, the metrology apparatus 200 may include a second normal incidence metrology tool 270. By way of example, the second metrology tool 270 may be configured for spectral reflectance measurements, spectral scatterometry measurements, overlap scatterometry measurements, interferometry measurements, electron beam metrology, X-ray metrology, FTIR measurements, etc. In some implementations, the metrology apparatus 200 may include additional tools, such as a third (or more) metrology tool. In some implementations, the additional metrology tools may be separate from the metrology apparatus 200.

[0036] The metrology apparatus 200 also includes one or more computing systems 260 configured to characterize one or more parameters of the sample 203 using the methods described herein. The one or more computing systems 260 are coupled to the first metrology tool 201 (e.g., the detector 250) and the second metrology tool 270, as well as any additional metrology tools (if present) to receive metrology data acquired during measurement of the structure of the sample 203. The acquisition of data may be performed during pre-processing manufacturing steps as well as during post-processing manufacturing steps. The one or more computing systems 260 may be, for example, a workstation, a personal computer, a central processing unit, or other suitable computer system, or multiple systems.

[0037] It should be understood that the one or more computing systems 260 may be a single computer system or multiple separate or linked computer systems, which are interchangeably referred to herein as computing system 260, at least one computing system 260, or one or more computing systems 260. The computing system 260 may be included in or connected to or otherwise associated with the metrology device 200 and any additional metrology tools. The different subsystems of the metrology device 200 may each include a computing system that is configured to perform steps associated with the associated subsystem. For example, the computing system 260 may control the positioning of the sample 203, for example, by controlling the movement of the stage 209 coupled to the chuck. The stage 209 may, for example, be capable of horizontal movement in Cartesian (i.e., X and Y) coordinates or polar (i.e., R and θ) coordinates, or some combination of the two. The stage may also be capable of vertical movement along the Z coordinate. The computing system 260 may further control the operation of the chuck 208 to hold or release the sample 203. The computing system 260 may further control or monitor the rotation of one or more polarization elements 204, 212 or additional elements 205a, 205b, etc.

[0038] The computing system 260 may be communicatively coupled to the detector 250 in the first metrology tool 201 and the detector in the second metrology tool 270 (if present) in any manner known in the art. For example, one or more computing systems 260 may be coupled to a separate computing system associated with the detector 250. The computing system 260 may be configured to receive and / or obtain metrology data from the detector 250 and the controller polarization elements 204, 212 and the additional elements 205a, 205b, etc. and the components of the second metrology tool 270 via a transmission medium that may include wired and / or wireless portions, for example. Thus, the transmission medium may serve as a data link between the computing system 260 and other subsystems of the metrology device 200. The computing system 260 may further be configured to receive and / or obtain additional information about the sample and one or more subsystems of the first metrology tool 201 and the production equipment, for example, from a user interface (UI) 268 or via a transmission medium that may include wired and / or wireless portions.

[0039] The computing system 260 includes at least one processor 262 with a memory 264, and a UI 268 communicatively coupled via a bus 261. The memory 264 or other non-transitory computer-usable storage medium includes computer-readable program code 266 embodied therein and can be used by the computing system 260 to cause at least one computing system 260 to control the metering device 200 and perform functions including the techniques and analyses described herein. For example, as illustrated in the figure, the memory 264 may include instructions for causing the processor 262 to perform both modeling and machine learning, and in some specific implementations, feedforward and / or feedback may be employed, as discussed herein. In view of the present disclosure, a person of ordinary skill in the art can implement the data structures and software codes described in this detailed description for automatically implementing one or more actions, and these data structures and software codes are stored on a computer-usable storage medium such as the memory 264, which can be any device or medium that can store code and / or data for use by a computer system such as the computing system 260. Computer usable storage media may be, but are not limited to, read-only memory, random access memory, magnetic and optical storage devices such as disk drives, magnetic tape, etc. In addition, the functions described herein may be embodied in whole or in part within the circuitry of an application specific integrated circuit (ASIC) or a programmable logic device (PLD), and these functions may be embodied in a computer understandable descriptor language that may be used to create an ASIC or PLD that operates as described herein.

[0040] The computing system 260, for example, may be configured to obtain data of a reference sample that may include a structure of interest (such as a 3D complex structure including, but not limited to, a GAA transistor) from a plurality of data sources (including one or both of the metrology tools 201 and 270) and any desired additional metrology tools, as well as data related to the sample (such as reference data and / or design of experiments (DOE) data) and data related to the metrology tool and / or process equipment (such as process parameters, advanced parameter control (APC) parameters, contextual data, and sensor data from production equipment). For example, the DOE data may be measurement data from a set of reference samples processed with intentionally introduced skew conditions such that the structural parameters of interest vary through the skewed processing conditions with a known pattern. The computing system 260 may be configured to generate and use one or more physical models (models 264pm) of the sample based on the measurement data from one or more reference samples and optionally additional information related to the sample and / or process equipment, and to generate, train, and use one or more machine learning models (ML 264ml) of the sample based on measurement results extracted from the one or more physical models and data, as discussed herein. In some embodiments, different computing systems and / or different metrology devices may be used to acquire metrology data and additional information from training samples and generate one or more physical models (model 264pm) and / or generate and train one or more machine learning models (ML264ml), and the resulting physical models and / or trained machine learning models (or portions thereof) may be provided to a computing system 260, for example, via computer readable program code 266 on a non-transitory computer-usable storage medium such as memory 264.

[0041] The computing system 260 may additionally or alternatively be used to obtain data from a test sample from a plurality of data sources. The data may be of the same type used to generate the physical model and to generate and train the machine learning model described above, and the test sample has the same structure as the reference sample, such as having an SOI. The computing system 260 may be configured to use data from a plurality of sources and one or more physical models (models 264pm) and one or more trained machine learning models (ML264ml) to determine one or more parameters of interest of the SOI, as discussed herein.

[0042] The results from the analysis of the data may be reported, for example, stored in a memory 264 associated with the sample 203 and / or indicated to a user via a UI 268, an alarm, or other output device. In addition, the results from the analysis may be reported and fed forward or fed back to the process equipment to adjust the appropriate manufacturing steps to compensate for any detected differences in the manufacturing process. For example, the computing system 260 may include a communication port 269, which may be any type of communication connection, such as a communication connection to the Internet or any other computer network. The communication port 269 may be used to receive instructions for programming the computing system 260 to perform any one or more of the functions described herein and / or to output, for example, a signal with measurement results and / or instructions to another system, such as an external process tool, in a feedforward or feedback process to adjust a process parameter associated with a manufacturing process step of the sample based on the measurement results.

[0043] As discussed herein, in order to characterize the SOI to be measured (e.g., including but not limited to complex 3D structures of GAA transistors), (1) at least one physics-based model is constructed to analyze metrology signals from one or more tools (such as spectroscopic ellipsometry (SE), spectroscopic reflectometry (SR), X-ray, electron beam, photoacoustic data, Fourier transform infrared spectroscopy (FTIR), etc.) and from one or more sources to extract measurement results of key parameters and non-key parameters. In addition, (2) at least one machine learning model is constructed and trained to predict the parameters of interest. The machine learning model can take multiple data of one of the following data as input: a) measurement results (key parameters and non-key parameters) from the physical model of (1); b) raw signals and optionally mismatches from the physical model of (1); data sources from different tool groups or the same tool in (1) but not included in the physical modeling; process parameters, APC parameters, context data; and sensor data from production equipment. In addition, (3) the physical model and machine learning model created and trained can be used to perform online measurement of SOI to predict the parameters of interest based on data from multiple data sources.

[0044] By way of example, Figure 3 A workflow 300 for offline recipe creation (e.g., generating one or more physical models and one or more machine learning models) according to a first example scenario is illustrated, wherein data is collected from multiple data sources (e.g., different tools and / or sources). Figure 3 In FIG. 3 , solid black arrows indicate processes used in workflow 300 , dashed black arrows indicate processes that are optional but at least one exists, and dashed grey arrows indicate optional processes.

[0045] As illustrated, measurement signals 302 from one or more reference samples are collected from a first data source or tool (Source 1). The measurement signals may be collected from any desired metrology equipment, such as Figure 2 ) or from any other desired type of metrology equipment to collect a measurement signal 302 from the SOI.

[0046] Additionally, data is acquired from one or more additional data sources. For example, in some implementations, measurement signals 304 and 306 from one or more reference samples may be collected from one or more additional sources or tools, such as illustrated as a second source or tool (Source 2) and a third source or tool (Source 3). For example, measurement signals 304 and 306 from one or more reference samples may be collected from one or more additional sources or tools, such as illustrated as a second source or tool (Source 2) and a third source or tool (Source 3). Figure 2Additional measured signals 304 may be collected from metrology tools 270 shown in Figure 1 or from any other desired type of metrology equipment, and measurement signals 306 may be collected from metrology equipment different from source 1 and source 2 (such as different types of measurements from either of metrology tools 201 or 270 or from any other desired type of metrology equipment). Additional data 308 related to the SOI may be collected and used as training data for one or more machine learning models 322, as illustrated by the box arrows. The additional data 308 may include, for example, reference data and DOE data of the sample. For example, the reference data may be measurement data acquired from one or more reference samples by a metrology equipment and values ​​of structural parameters of interest, typically provided by a CD-AFM (atomic force microscope), a CD-SEM (scanning electron microscope), or a TEM (transmission electron microscope). The reference data and / or DOE data may be used as a training data set to train a machine learning model to find relevant data features and learn the inherent relationships and connections between input features and output features in order to make decisions and predictions on new data. In some implementations, the additional data 308 associated with the reference sample may further include wafer condition, accuracy, tool matching data, etc., accuracy data (for example) being a parameter based on data from the same target repeatedly measured from the same tool instance at multiple times. Accuracy is another metrology key performance indicator (KPI) that indicates the consistency of measurement results from multiple runs of the same sample. Tool matching data is, for example, a parameter based on measurement data of the same sample from multiple instances of a tool of the same tool type. Tool matching is another metric KPI that indicates the consistency of measurement results from different tools of the same type for the same sample. Measurement accuracy (assessed by matching with reference values ​​provided from CD-AFM, CD-SEM, TEM, etc. and / or consistency with DOE conditions), accuracy, and tool matching are typical metrology KPIs. If accuracy and tool matching data are provided, physical modeling or machine learning models can be optimized to not only closely match reference values, but also predict consistent results for the same sample using measurement signals from multiple runs of the same tool or from different tools of the same type.

[0047] In addition, in some specific implementations, the additional data signal 309 can be used as an input to the physical model or an input feature to the machine learning model. For example, additional data signals 309 that can be associated with sources (e.g., source 1, source 2, and source 3) such as process parameters, advanced process control (APC) parameters, contextual data, and sensor data from production equipment can be obtained. By way of example, some process control parameters (e.g., substrate temperature and chemical concentration for wet etching) can affect the etching rate (the speed at which material is removed from the surface of the wafer), and the etching rate is one of the important factors in determining the etching depth and CD profile. Some of these parameters (such as temperature) are measured by sensors from production equipment. Other parameters (such as etching time, etching chamber name) are user-controlled parameters. The name of the etching chamber is an example of contextual data. Since each etching chamber has its own characteristic distribution of etching profiles across the wafer, knowing this information can help machine learning predict the correct wafer map. An example of an APC parameter is an atomic force microscope (AFM) result that is measured from the same sample in different processing steps, which contains relevant information, such as non-critical parameters of the structure of interest. Adding non-critical parameters as machine learning input features can help improve the robustness of machine learning in predicting critical parameters. Adding all of these relevant parameters as machine learning input features can provide additional information that helps determine the structural parameters of interest that are controlled by these process parameters and conditions.

[0048] Measurement signals and data from multiple data sources can be used to generate one or more physical models of the SOI. For example, as illustrated by the black solid arrow, the measurement signal 302 from the first source (source 1) can be used to generate a first physical model 312 of the sample. For example, the physical model of the sample is created based on the known geometry, nominal values, and materials of the structure. The measurement signal 302 can be used to generate the first physical model 312 by providing data from which the measurement results are extracted, and the first physical model 312 can be adjusted and optimized so that the calculated signal is well fitted to the measured signal and a good match between the extracted measurement results and the known parameters of the reference sample is achieved. In some specific implementations, additional data can be used to help generate the first physical model 312. For example, as illustrated by the gray dashed arrow, additional data 308 (such as reference data and / or DOE) and optionally wafer condition, precision, and tool matching data can also be used to help generate the first physical model 312. In addition, as illustrated by the gray dashed arrow, the data signal 309 can be used to help generate the first physical model 312. In another example, as illustrated by the dashed grey arrow, the measurement signal 304 from the second source (Source 2) can be used to help generate the first physical model 312 of the sample. In some implementations, both the additional data 308 and the measurement signal 304 can be used to help generate the first physical model 312.

[0049] In some implementations, multiple physical models can be generated. For example, as illustrated by the gray dashed arrow and the gray dashed box, a second physical model 314 can be generated based on the measurement signal 304 from the second source (source 2). In some implementations, additional data can be used to generate the second physical model 314. For example, as illustrated by the gray dashed arrow, additional data 308 (such as reference data and / or DOE) and optionally wafer condition, precision and tool matching data can also be used to help generate the second physical model 314. In another example, as illustrated by the gray dashed arrow, the measurement signal 306 from the third source (source 3) can be used to help generate the second physical model 314 of the sample. In some implementations, both the additional data 308 and the measurement signal 306 can be used to help generate the second physical model 314. In addition, as illustrated by the gray dashed arrow, the data signal 309 can be used to help generate the second physical model 314. In addition, multiple physical models can be optimized independently or jointly. For example, in some implementations, as illustrated by the gray dashed line, the first physical model 312 and the second physical model 314 can be linked so that at least some parameters can be coupled across the physical models 312 and 314, and the combined parameter space can be searched to fit the measurement signals from one or more data sources. The first physical model 312 and optionally the second physical model 314 can be configured to provide a goodness of fit 323 of the physical modeling.

[0050] One or more machine learning models 322 are built and trained using multiple data sources to predict parameters of interest 325. Machine learning measurement indicators 327 can be developed and reported together with goodness of fit from physical modeling to indicate the quality of measurements from the formulation of physical modeling and machine learning collaboration. As illustrated by the solid black arrows, the machine learning model 322 is built using the measurements extracted by the first physical model 312 as input features. As indicated by the dashed black arrows, the input features of the machine learning model 322 may additionally include at least one of measurement signals 304 from one or more reference samples collected from the second source (source 2), measurement signals 306 from one or more reference samples collected from the third source (source 3), additional data signals 309, measurements extracted by the second physical model 314, or any combination thereof. In some implementations, as illustrated by the dashed grey arrows, the input features of the machine learning model 322 may optionally include measurement signals 302 from one or more reference samples collected from the first source (source 1). In some implementations, the input features from the measurement signal 302 may include data channels or data blocks that are not used in generating the first physical model 312. For example, in general, a data channel may be a measurement subsystem defined by at least one of an energy source such as a light source, an optical path guided by an optical component, a detector, or any combination thereof, and a data block may be a subset of wavelength (e.g., as used in spectroscopic metrology), frequency (e.g., as used in frequency-resolved metrology), angle (e.g., as used in angle-resolved metrology), time span (e.g., as used in time-resolved metrology), or any combination of the above from the complete data set provided by the data channel. For example, the first metrology device may collect a normal incidence signal and an oblique incidence spectroscopic ellipsometer (SE) signal. The SE signal may be used to generate the first physical model 312, but the normal incidence signal may not be used because it may be difficult to fit the normal incidence signal. Therefore, in addition to the physical modeling results generated from different data channels (e.g., SE signals), the normal incidence signal may be a data channel of data used as an input feature of the machine learning model 322. In another example, the same data channel may be divided into multiple data blocks (e.g., signals from different wavelength ranges), and some data blocks may be difficult to fit using physical modeling but may be used as data for input features of the machine learning model 322.

[0051] The machine learning model 322 is trained with at least a portion of data 308 such as reference data and / or DOE, and optionally with wafer condition, precision, and tool matching data. Data 308 is training data and is used for offline training. For example, the reference data can be a set of signals (e.g., including any of the measurement results from the first physical model 312, the measurement signal 304, the measurement signal 306, the additional data signal 309, and the measurement signal 302) with labels (e.g., values ​​of key parameters provided by other metrology systems such as CD-SEM, TEM, CD-AFM). During the training of the machine learning model 322, the set of signals from the reference data is used as machine learning input features, and based on these input features, the machine learning model 322 predicts the key parameters. The machine learning model 322 is trained to learn and make predictions of key parameters that match the labels of the reference data. The DOE from data 308 is a set of signals measured from a reference sample processed with intentionally introduced skew conditions (e.g., including any one of the measurement results from the first physical model 312, the measurement signal 304, the measurement signal 306, the additional data signal 309, and the measurement signal 302). During machine learning training, the machine learning model 322 takes the signals from the DOE data as input features and predicts the key parameters. The machine learning model 322 is trained so that the predicted key parameter values ​​follow the expected skew pattern based on the process skew conditions. The precision data from data 308 is the measurement signal from the same sample but on multiple runs from the same metrology tool (e.g., including any one of the measurement results from the first physical model 312, the measurement signal 304, the measurement signal 306, the additional data signal 309, and the measurement signal 302). Similarly, tool matching data from data 308 is a signal from the same sample but measured from different instances of the same type of metrology tool (e.g., including any of the measurement results from the first physical model 312, the measurement signal 304, the measurement signal 306, the additional data signal 309, and the measurement signal 302). The machine learning model 322 takes the accuracy and tool matching data as input features and makes predictions. The machine learning model 322 is trained so that the predicted values ​​of the key parameters are consistent for signals measured from the same sample but from different runs or different tools. The machine learning model 322 can be trained so that if all of this data is provided during training, all criteria, matching to reference values, DOE skew conditions, high accuracy, and consistent tool matching are met simultaneously.

[0052] By way of example, Figure 4 A workflow 400 for online measurement according to a first example scenario is illustrated, for example, for characterizing a sample based on one or more physical models and one or more machine learning models, where signals are collected from multiple data sources (e.g., different tools and / or sources). Figure 4 One or more physical models and one or more machine learning models are generated as discussed above. Figure 4 In FIG. 4 , solid black arrows indicate processes used in workflow 400 , dashed black arrows indicate processes that are optional but for which at least one exists, and dashed grey arrows indicate optional processes.

[0053] As illustrated, a measurement signal 402 of the SOI of a sample is collected from a first data source or tool (Source 1). The measurement signal 402 may be collected from any desired metrology equipment such as Figure 2 201) or from any other desired type of metrology equipment and can be collected from Figure 3 The same metering device or the same type of metering device in source 1 is collected.

[0054] Additionally, data is obtained from one or more additional data sources. For example, in some implementations, measurement signals 404 and 406 can be collected from one or more additional sources or tools, which are shown, for example, as a second source or tool (Source 2) and a third source or tool (Source 3). For example, additional measurement signal 404 can be collected from a metrology device other than Source 1, such as Figure 2 270) or from any other desired type of metrology equipment and can be collected from the same Figure 3 The measurement signals 406 may be collected from the same metrology device or the same type of metrology device as source 2 in source 1 and source 2 (such as different types of measurements from either metrology tool 201 or 270 or from any other desired type of metrology device), and may be collected from the same metrology device or the same type of metrology device as used for source 1 and source 2. Figure 3 In addition, in some implementations, additional data signals 409 may be obtained, such as process parameters, APC parameters, context data, and sensor data from production equipment, which may be related to the sources (e.g., source 1, source 2, and source 3).

[0055] Signals and data from multiple data sources can be used to extract measurements from one or more physical models. For example, as illustrated by the solid black arrow, a measurement signal 402 from a first source (Source 1) can be used to extract measurements of the SOI of a sample from a first physical model 412, which can be compared to Figure 3 4. In some implementations, additional data can be used to help extract measurements from the first physical model 412. For example, as illustrated by the gray dashed arrow, a measurement signal 404 from a second source (Source 2) can be used to help extract measurements from the first physical model 412 of the sample.

[0056] Additionally, as illustrated by the grey dashed arrow, additional data signal 409 may be used to assist in extracting measurements of the sample from first physical model 412 .

[0057] In some implementations, multiple physical models can be used to extract measurement results for a sample. For example, as illustrated by the gray dashed arrow and gray dashed box, the second physical model 414 can be used to extract measurement results for the sample based on the measurement signal 404 from the second source (source 2). For example, the second physical model 414 can be used with Figure 3 414. In some embodiments, additional data can be used to help extract measurements from the second physical model 414. For example, as illustrated by the gray dashed arrow, the measurement signal 406 from the third source (source 3) can be used to help extract the measurement results of the sample from the second physical model 414. In addition, as illustrated by the gray dashed arrow, the additional data signal 409 can be used to help extract the measurement results of the sample from the second physical model 414. In addition, multiple physical models can be optimized independently or jointly. For example, in some embodiments, as illustrated by the gray dashed line, the first physical model 412 and the second physical model 414 can be linked so that at least some parameters can be coupled across the physical models 412 and 414, and the combined parameter space can be searched to fit the measurement signals from one or more data sources. The first physical model 412 and optionally the second physical model 414 can be configured to provide a goodness of fit 423 for physical modeling.

[0058] One or more trained machine learning models 422 are used to predict parameters of interest 425 based on multiple data sources. Machine learning measurement indicators 427 and goodness of fit 423 from physical modeling can be reported to indicate the quality of the measurements from the collaborative formulation of physical modeling and machine learning. For example, the trained machine learning model 422 can be used with Figure 3The trained machine learning model 422 is the same as the machine learning model 322. As illustrated by the solid black arrow, the trained machine learning model 422 uses the measurement results extracted by the first physical model 412 as input features. As indicated by the dashed black arrow, the trained machine learning model 422 may also use input features, which include at least one of the following: a measurement signal 404 from a sample collected from a second source (source 2), a measurement signal 406 from a sample collected from a third source (source 3), an additional data signal 409, and a measurement result extracted by the second physical model 414 based on the additional measurement signal 404 and / or 406, or any combination thereof. In some specific implementations, as illustrated by the dashed gray arrow, the trained machine learning model 422 may optionally also use input features including the measurement signal 402 from the sample collected from the first source (source 1). In some specific implementations, the machine learning input features from the measurement signal 402 may include data channels or data blocks that are not used when extracting the measurement results from the first physical model 412, such as reference Figure 3 discussed.

[0059] By way of example, Figure 5 A workflow 500 for offline recipe creation (e.g., generating one or more physical models and one or more machine learning models) according to a second example scenario is illustrated, where signals are collected from multiple data sources (e.g., different manufacturing process steps). Figure 5 In FIG. 5 , solid black arrows indicate processes used in workflow 500 , dashed black arrows indicate processes that are optional but at least one exists, and dashed grey arrows indicate optional processes.

[0060] As illustrated, post-processing step measurement signals 502 are measured from one or more reference samples from a metrology device. For example, the reference sample may be an OCD target pad or a semiconductor device, and the post-processing step measurement signals 502 are obtained after completing the desired manufacturing steps of the sample. The post-processing step measurement signals 502 may be obtained from any desired metrology device (e.g., Figure 2 ) or collect post-processing step measurement signals 502 from any other desired type of metrology equipment.

[0061] Additionally, pre-processing step measurement signals 502 from one or more reference samples are measured using a metrology device (e.g., the same metrology device used to acquire the post-processing step measurement signal 504) and used to generate pre-processing step data. For example, the pre-processing step measurement signal 504 is obtained prior to completing a desired manufacturing step for the sample. In some implementations, the post-processing step measurement signal 502 and the pre-processing step measurement signal 504 may be combined (e.g., combined by addition, subtraction, multiplication, or division) to form a pre-conditioned signal 505. Additionally, data 508 related to the reference samples may be collected, such as reference data for the samples, a design of experiments (DOE). In some implementations, additional data 508 related to the reference samples may also include wafer condition, accuracy, tool matching data, and the like. Additionally, data may be obtained from other sources, such as from a second measurement pad 506, from a fault detection pad 509, or any combination thereof. Although Figure 3 and Figure 4 The first example scenario in emphasizes multiple data sources collected from different metrology equipment, but the second example scenario (for example) illustrates that the multiple data sources can come from different measurement pads or the same pad at different process steps. Different measurement pads can be measured from the same or different metrology equipment. The pre-processing step measurement signal 504 and the post-processing step measurement signal 502 can be measured on a designed OCD target or device. For example, the second measurement pad 506 refers to a pre-processing step measurement and / or post-processing step measurement from a measurement pad that is not measured for the pre-processing step measurement signal 504 and the post-processing step measurement signal 502. For example, if the pre-processing step measurement signal 504 and the post-processing step measurement signal 502 are measured on the OCD target, the second measurement pad 506 can refer to a signal from a device pad, or vice versa.

[0062] Signals and data from multiple data sources can be used to generate one or more physical models. For example, as illustrated by the solid black arrow, a post-processing step measurement signal 502 from a metrology device can be used to generate a post-processing physical model 512 of a sample. In some implementations, additional data can be used to help generate the post-processing physical model 512. For example, as illustrated by the dashed gray arrow, additional data 508 (such as reference data and / or DOE) and optionally wafer condition, precision and tool matching data can also be used to help generate the post-processing physical model 512. In another example, as illustrated by the dashed gray arrow, a pre-conditioning signal 505 can be used to help generate a post-processing physical model 512 of a sample. In another example, as illustrated by the dashed gray arrow, a signal from a second measurement pad 506 can be used to help generate a post-processing physical model 512 of a sample. In another example, as illustrated by the dashed gray arrow, a signal from a fault detection pad 509 can be used to help generate a post-processing physical model 512 of a sample. In some implementations, all or any combination of the data 508 and signals from different measurement pads (eg, the second measurement pad 506 and / or the fault detection pad 509 ) can be used to help generate the post-processing physics model 512 .

[0063] In some implementations, multiple physical models can be generated. For example, as illustrated by the gray dashed arrow and the gray dashed box, a pre-processing physical model 514 can be generated based on the pre-processing step measurement signal 504 from the metrology equipment. In some implementations, additional data can be used to generate the pre-processing physical model 514. For example, as illustrated by the gray dashed arrow, additional data 508 (such as reference data and / or DOE) and optionally wafer condition, precision and tool matching data can also be used to help generate the pre-processing physical model 514. In another example, as illustrated by the gray dashed arrow, the signal from the second measurement pad 506 can be used to help generate the pre-processing physical model 514 of the sample. In another example, as illustrated by the gray dashed arrow, the signal from the fault detection pad 509 can be used to help generate the pre-processing physical model 514 of the sample. In some implementations, all or any combination of data 508 and the signals from the second measurement pad 506 and the fault detection pad 509 can be used to help generate the pre-processing physical model 514. In addition, multiple physical models can be optimized independently or together. For example, in some implementations, as illustrated by the gray dashed line, the post-processing physical model 512 and the pre-processing physical model 514 can be linked so that at least some parameters can be coupled across the post-processing physical model 512 and the pre-processing physical model 514, and the combined parameter space can be searched to fit the measurement signals from one or more data sources. The post-processing physical model 512 and optionally the pre-processing physical model 514 can be configured to provide a goodness of fit 523 of the physical modeling.

[0064] One or more machine learning models 522 are built and trained using multiple data sources to predict parameters of interest 525. Machine learning measurement indicators 527 can be developed and reported along with goodness of fit 523 from physical modeling to indicate the quality of measurements from the formulation of physical modeling and machine learning collaboration. As illustrated by the solid black arrows, the machine learning model 522 is built using post-processing measurements extracted by the post-processing physical model 512 as input features. As indicated by the dashed black arrows, the input features of the machine learning model 522 also include pre-processing step data generated based on the pre-processing step measurement signal 504. The pre-processing step data can be generated based on the pre-processing step measurement signal 504 in a variety of ways. For example, Figure 5 As illustrated, pre-processing step data can be generated from pre-processing step measurement signal 504 in three different ways labeled 1, 2, and 3, wherein at least one of (1), (2), or (3) or any combination thereof is used. As illustrated by label 1 for pre-processing step measurement signal 504, pre-processing step data can be generated by combining pre-processing step measurement signal 504 with post-processing step measurement signal 502 to form pre-conditioned signal 505. Figure 5 As described in , in some implementations, if a pre-conditioned signal 505 is generated, the pre-conditioned signal 505 may be (A) provided to the post-processing physical model 512 and the machine learning model 522 constructed based at least in part on the post-processing measurements extracted by the post-processing physical model 512, or (B) the pre-conditioned signal 505 is provided to the machine learning model 522 and the machine learning model 522 is constructed based at least in part on the pre-conditioned signal 505. In addition, as Figure 5 As further described in , in some implementations, at least one of (A) or (B) can be used with the workflow 500. As illustrated by the label 2 for the pre-processing step measurement signal 504, the pre-processing step data can be generated by providing the pre-processing step measurement signal 504 to the pre-processing physical model 514, and the machine learning model 522 can be constructed based at least in part on the pre-processing measurement results extracted by the pre-processing physical model 514. As illustrated by the label 3 for the pre-processing step measurement signal 504, the pre-processing step data can be generated by providing the pre-processing step measurement signal 504 to the machine learning model 522, and the machine learning model 522 can be constructed based at least in part on the pre-processing step measurement signal 504.

[0065] In addition, as illustrated by the black dashed arrow, the machine learning model 522 is constructed using additional data including at least one of the following: the pre-processing step measurement signal 504 (i.e., at least one of (1), (2), or (3) of the pre-processing step measurement signal 504, or any combination thereof), the signal from the second measurement pad 506, and the signal from the fault detection pad 509, or any combination thereof. In some specific implementations, as illustrated by the gray dashed arrow, the machine learning model 522 can optionally be further constructed using the post-processing step measurement signal 502, the pre-conditioned signal 505, the measurement results extracted by the pre-processing physical model 514, or some combination thereof.

[0066] The machine learning model 522 is trained with at least a portion of the data 508, such as reference data and / or DOE, and optionally with wafer condition, accuracy, and tool matching data.

[0067] By way of example, Figure 6 A workflow 600 for online measurement according to a second example scenario is illustrated, for example, for characterizing a sample based on one or more physical models and one or more machine learning models, where signals are collected from multiple data sources (e.g., different manufacturing process steps). Figure 5 One or more physical models and one or more machine learning models are generated as discussed above. Figure 6 In FIG. 6 , solid black arrows indicate processes used in workflow 600 , dashed black arrows indicate processes that are optional but for which at least one exists, and dashed grey arrows indicate optional processes.

[0068] As illustrated, a post-processing step measurement signal 602 is collected from a sample from a metrology device. For example, the sample may be an OCD target pad or a semiconductor device, and the post-processing step measurement signal 602 is obtained after completing the desired manufacturing steps of the sample. The post-processing step measurement signal 602 may be collected from any desired metrology device, such as a Figure 2 201) or from any other desired type of metrology equipment and can be obtained from the same Figure 5 The post-processing step in measurement signal 502 is collected by the same metrology device or the same type of metrology device.

[0069] Additionally, a pre-processing step measurement signal 604 is collected from the sample using a metrology device, such as the same metrology device used to obtain the post-processing step measurement signal 602 and the same metrology device used to obtain the post-processing step measurement signal 604. Figure 5The pre-processing step measurement signal 604 is the same metrology device or the same type of metrology device as the pre-processing step measurement signal 504 in the sample. The pre-processing step measurement signal 604 is used to generate pre-processing step data. For example, the pre-processing step measurement signal 604 is obtained before the required manufacturing steps of the sample are completed. In some specific implementations, the post-processing step measurement signal 602 and the pre-processing step measurement signal 604 can be combined (for example, combined by addition, subtraction, multiplication or division) to form a pre-conditioning signal 605. In addition, data can be obtained from other sources, such as from a second measurement pad 606, from a fault detection pad 609, or any combination thereof. The pre-processing step measurement signal 604 and the post-processing step measurement signal 602 can be measured on a designed OCD target or device. For example, the second measurement pad 606 refers to a pre-processing step measurement and / or a post-processing step measurement from a measurement pad that is not measured for the pre-processing step measurement signal 604 and the post-processing step measurement signal 602. For example, if the pre-processing step measurement signal 604 and the post-processing step measurement signal 602 are measured on an OCD target, the second measurement pad 606 may refer to an auxiliary signal from a device pad, or vice versa.

[0070] Signals and data from multiple data sources can be used to extract measurements from one or more physical models. For example, as illustrated by the solid black arrow, the post-processing step measurement signal 602 can be used to extract measurements of the sample from the post-processing physical model 612, which can be used with Figure 5 6. In some implementations, additional data may be used to help extract measurements from the post-processing physical model 612. For example, as illustrated by the gray dashed arrow, the pre-conditioned signal 605 may be used to help extract measurements from the post-processing physical model 612 of the sample. In another example, as illustrated by the gray dashed arrow, the signal from the second measurement pad 606 may be used to help extract measurements from the post-processing physical model 612 of the sample. In another example, as illustrated by the gray dashed arrow, the signal from the fault detection pad 609 may be used to help extract measurements from the post-processing physical model 612 of the sample. In some implementations, all or any combination of the signals from the second measurement pad 606 and the fault detection pad 609 may be used to help extract measurements from the post-processing physical model 612.

[0071] In some implementations, multiple physical models can be used to extract the measurement results of the sample. For example, as illustrated by the black dashed arrow and the black dashed box, the pre-processing physical model 614 can be used to extract the measurement results of the sample based on the pre-processing step measurement signal 604. The pre-processing physical model 614 can be used with Figure 5The post-processing physical model 612 and the pre-processing physical model 614 may be the same as the pre-processing physical model 614 in . In addition, multiple physical models may be optimized independently or jointly. For example, in some implementations, as illustrated by the gray dashed line, the post-processing physical model 612 and the pre-processing physical model 614 may be linked so that at least some parameters may be coupled across the post-processing physical model 612 and the pre-processing physical model 614, and the combined parameter space may be searched to fit the measurement signals from one or more data sources. The post-processing physical model 612 and optionally the pre-processing physical model 614 may be configured to provide a goodness of fit 623 for physical modeling.

[0072] One or more trained machine learning models 622 are used to predict parameters of interest 625 based on multiple data sources. Machine learning measurement indicators 627 can be developed and reported together with goodness of fit 623 from physical modeling to indicate the measurement quality of the recipe from physical modeling and machine learning collaboration. As illustrated by the black solid arrows, the trained machine learning model 622 uses the post-processing measurement results extracted by the post-processing physical model 612 as input data, as well as pre-processing step data generated based on the pre-processing step measurement signal 604.

[0073] The pre-processing step data can be generated in a variety of ways based on the pre-processing step measurement signal 604. For example, Figure 6 As illustrated, pre-processing step data can be generated from pre-processing step measurement signal 604 in three different ways labeled 1, 2, and 3, wherein at least one of (1), (2), or (3) or any combination thereof is used. As illustrated by label 1 for pre-processing step measurement signal 604, pre-processing step data can be generated by combining pre-processing step measurement signal 604 with post-processing step measurement signal 602 to form pre-conditioned signal 605. Figure 6 As described in , in some implementations, if a pre-conditioned signal 605 is generated, the pre-conditioned signal 605 can be (A) provided to the post-processing physical model 612 and the trained machine learning model 622 receives input data in the form of post-processing measurement results extracted by the post-processing physical model 612, or (B) the pre-conditioned signal 605 is provided to the trained machine learning model 622 as input data. In addition, as Figure 6As further described in , in some implementations, at least one of (A) or (B) can be used with workflow 600. As illustrated by label 2 for pre-processing step measurement signal 604, pre-processing step data can be generated by providing pre-processing step measurement signal 604 to pre-processing physics model 614, and trained machine learning model 622 uses the measurement results extracted by pre-processing physics model 614 as input data. As illustrated by label 3 for pre-processing step measurement signal 604, pre-processing step data can be generated by providing pre-processing step measurement signal 604 as input data to trained machine learning model 622.

[0074] In some implementations, as illustrated by the grey dashed arrow, the trained machine learning model 622 may optionally also use input data including a post-processing step measuring the signal 602 .

[0075] By way of example, Figure 7 A workflow 700 for offline recipe creation (e.g., generating one or more physical models and one or more machine learning models) according to a third example scenario is illustrated, where signals are collected from multiple data sources (e.g., different manufacturing process steps). For example, the workflow 700 based on the third example scenario can be applied to the measurement of complex 3D structures (including but not limited to GAA transistors or other devices), and provides a method for independently measuring different CDs of structures of interest (such as SiGe layers and internal spacer critical dimensions (CDs) in logic GAA devices) using the hybrid metrology and ecosystem framework discussed herein, such as Figure 1A and Figure 1B As discussed in Figure 7 In FIG. 7 , solid black arrows indicate processes used in workflow 700 , while dashed grey arrows indicate optional processes.

[0076] As illustrated, post-processing step measurement signals 702 from one or more reference samples are collected from a metrology device. For example, the reference sample includes SOI, and the post-processing step measurement signals 702 are obtained after completing the desired manufacturing steps of the sample. The post-processing step measurement signals 702 may be, for example, spectral data and may be obtained from any desired metrology device (e.g., Figure 2 ) or collected from any other desired type of metrology equipment.

[0077] Additionally, pre-processing step measurement signals 702 from one or more reference samples are collected using a metrology device (e.g., the same metrology device used to acquire post-processing step measurement signals 704) and used to generate pre-processing step data. For example, pre-processing step measurement signals 704 are obtained from a reference sample, such as a SOI, and are obtained prior to completing a desired manufacturing step of the sample. Pre-processing step measurement signals 704 may be, for example, spectral data and may be collected from the same or different metrology device as used to collect post-processing step measurement signals 702, which may be any desired metrology device, such as Figure 2 , or collected from any other desired type of metrology equipment. In some implementations, the post-processing step measurement signal 702 and the pre-processing step measurement signal 704 can be combined (e.g., combined by addition, subtraction, multiplication, or division) to form a pre-conditioned signal 705.

[0078] Additionally, post-processing step data 708 may be collected related to the SOI of the reference sample at a post-processing step (e.g., after completing the desired manufacturing steps for the sample), such as reference data and / or DOE for the sample. In some implementations, the additional post-processing step data 708 related to the reference sample may also include wafer condition, precision, tool matching data, etc. Additionally, pre-processing step data 709 may be collected related to the SOI of the reference sample at a pre-processing step (e.g., before completing the desired manufacturing steps for the sample), such as reference data and / or DOE for the sample. In some implementations, the additional pre-processing step data 709 related to the reference sample may also include wafer condition, precision, tool matching data, etc.

[0079] Signals and data from multiple data sources may be used to generate multiple physical models, such as a pre-processing physical model 714 and a post-processing physical model 712. For example, as illustrated by the solid black arrow, a pre-processing step measurement signal 704 from a metrology device may be used to generate a pre-processing physical model 714 of an SOI from a sample. In some implementations, additional data may be used to help generate the pre-processing physical model 714. For example, as illustrated, additional pre-processing step data 709 (such as reference data and / or DOE) and optionally wafer condition, accuracy, and tool matching data may also be used to help generate the pre-processing physical model 714.

[0080] In addition, a pre-processing machine learning model 724 is constructed and trained to predict one or more parameters of interest (parameter #1) 725. As illustrated by the solid black arrow, the pre-processing machine learning model 724 is constructed using the pre-processing measurements extracted by the pre-processing physical model 714 as input features. The pre-processing machine learning model 724 may also be constructed using the pre-processing step measurement signal 704 as an input feature. The pre-processing machine learning model 724 is trained with at least a portion of the pre-processing step data 709 (such as reference data and / or DOE) and optionally with wafer condition, precision, and tool matching data. The one or more parameters of interest (parameter #1) may include critical parameters (i.e., parameters to be measured at the current processing step) or non-critical parameters (i.e., parameters that are not expected parameters to be measured), or both critical parameters and non-critical parameters. By way of example, the parameter of interest (parameter #1) may be the Si / SiGe thickness of a GAA transistor, but other parameters of interest, including critical parameters or non-critical parameters, may be determined for a GAA transistor or for other devices being measured.

[0081] In addition, as illustrated by the solid black arrow, the post-processing step measurement signal 702 from the metrology equipment can be used to generate a post-processing physical model 712 of the SOI of the sample. In some specific implementations, additional data can be used to help generate the post-processing physical model 712. For example, as illustrated, additional post-processing step data 708 (such as reference data and / or DOE) and optionally wafer condition, accuracy and tool matching data can also be used to help generate the post-processing physical model 712. The pre-processing step measurement signal 704 contains rich information and sensitivity to one or more parameters of interest (parameter #1) 725, so such information can be used to improve accuracy. Therefore, as illustrated, the post-processing physical model 712 can receive feed-forward data from the pre-processing physical model 714 and / or from the pre-processing machine learning model 724, for example, for one or more parameters of interest (parameter #1) 725, so as to propagate information in the pre-processing manufacturing step signal to the post-processing physical model 712. In some specific implementations, feedback data generated based on the post-processing step measurement signal 702 can be used to help generate the post-processing physical model 712. As illustrated, the post-processing physics model 712 may receive feedback data of one or more parameters of interest (parameter #2) 723, determined by the post-processing machine learning model 722 as discussed below based on the post-processing step measurement signal 702. The accuracy of the one or more parameters of interest (parameter #2) 723 benefits from the more accurate one or more parameters of interest (parameter #1) 725 being fed forward to the post-processing physics model 712. In addition, the feedback of the one or more parameters of interest (parameter #2) 723 may break the high correlation of the parameters of interest (e.g., SiGe CD of different etches) that undergo the same manufacturing step. For example, the post-processing physics model 712 or the post-processing machine learning model 722 may use the feedback data and may be retrained with additional post-processing step data 708 (such as reference data and / or DOE) and optionally wafer condition, accuracy, and tool matching data to provide better predictions of other parameters of interest (e.g., (parameter #3) 713 or (parameter #2) 723).

[0082] A post-processing machine learning model 722 is constructed and trained to predict one or more parameters of interest (parameter #2) 723, which may include critical parameters, non-critical parameters, or both critical parameters and non-critical parameters. As illustrated by the solid black arrow, the post-processing measurement results extracted by the post-processing physical model 712 are used as input features to construct the post-processing machine learning model 722. The post-processing machine learning model 722 may also be constructed with the post-processing step measurement signal 702 as an input feature. In addition, as illustrated by the gray dashed line, the pre-conditioning signal 705 and / or the pre-processing step measurement signal 704 may be optionally used as input features to construct the post-processing machine learning model 722. The post-processing machine learning model 722 is trained with at least a portion of the post-processing step data 708 (such as reference data and / or DOE) and optionally with wafer condition, accuracy, and tool matching data. Parameters (e.g., hyperparameters, weights, biases, etc.) of the post-processing machine learning model 722 and the post-processing physical model 712 may be provided (e.g., reported) for characterizing the sample.

[0083] As illustrated, the post-processing physics model 712 (or a separate machine learning model) may be used to predict one or more additional parameters of interest, as illustrated by parameter #3 713, which may include critical parameters, non-critical parameters, or both. By way of example, the post-processing parameters of interest (e.g., parameters #2 and #3) 723 and 713 for GAA transistors (e.g., Figure 1B ) may be SiGe CD1, SiGe CD2, SiGe CD3, respectively, but other parameters of interest may be determined for GAA transistors or for other devices being measured. Figure 7 The workflow 700 illustrated in FIG. 7 can also be applied to other pre-processing steps and post-processing steps, such as multiple CD profile measurements in high aspect ratio (HAR) channel hole etching, etc. In addition, the additional parameter of interest (parameter #3) 713 can be further fed forward from the post-processing physical model 712 to the post-processing machine learning model 722. The post-processing machine learning model 722 can be retrained with at least a portion of the post-processing step data 708 to make a final prediction of the additional parameter of interest (parameter #3) 713.

[0084] By way of example, Figure 8 A workflow 800 for online measurement according to a third example scenario is illustrated, for example, for characterizing a sample based on one or more physical models and one or more machine learning models, where signals are collected from multiple data sources (e.g., different manufacturing process steps). Figure 7 One or more physical models and one or more machine learning models are generated as discussed above. Figure 8In FIG. 8 , solid black arrows indicate processes used in workflow 800 , while dashed gray arrows indicate optional processes.

[0085] As illustrated, post-processing step measurement signals 802 are collected from one or more reference samples from a metrology device. For example, the reference sample includes SOI, and the post-processing step measurement signals 802 are obtained after completing the desired manufacturing steps of the sample. The post-processing step measurement signals 802 can be, for example, spectral data and can be obtained from any desired metrology device (such as Figure 2 201) or from any other desired type of metrology equipment and may be collected from any device used to obtain Figure 7 The post-processing step in measurement signal 702 is collected by the same metrology device or the same type of metrology device.

[0086] Additionally, pre-processing step measurement signals 802 from one or more reference samples are collected using a metrology device (e.g., the same metrology device used to acquire post-processing step measurement signals 804) and used to generate pre-processing step data. For example, pre-processing step measurement signals 804 are obtained from a reference sample, such as a SOI, and are obtained prior to completing a desired manufacturing step of the sample. Pre-processing step measurement signals 804 may be, for example, spectral data and may be collected from the same or different metrology device as used to collect post-processing step measurement signals 802, which may be any desired metrology device, such as Figure 2 The metrology tool 201 or 270 shown in FIG. 1 , or collected from any other desired type of metrology equipment, and may be used to obtain Figure 7 In some implementations, the post-processing step measurement signal 802 and the pre-processing step measurement signal 804 can be combined (e.g., combined by addition, subtraction, multiplication, or division) to form the pre-conditioned signal 805.

[0087] Signals and data from multiple data sources may be used to extract measurements from multiple physical models, such as pre-processing physical model 814 and post-processing physical model 812. For example, as illustrated by the solid black arrow, a pre-processing step measurement signal 804 from a metrology device may be used to extract measurements from a pre-processing physical model 814 of an SOI from a sample.

[0088] In addition, the trained pre-processed machine learning model 824 is used to predict one or more parameters of interest (parameter #1) 825. As illustrated by the solid black arrow, the trained pre-processed machine learning model 824 uses the pre-processed measurement results extracted by the pre-processed physical model 814 as input features. The trained pre-processed machine learning model 824 may also use the pre-processing step measurement signal 804 as an input feature. The one or more parameters of interest (parameter #1) may include critical parameters, non-critical parameters, or both critical parameters and non-critical parameters, and by way of example, may be the Si / SiGe thickness of a GAA transistor, but other parameters of interest may be determined for a GAA transistor or for other devices being measured.

[0089] Additionally, as illustrated by the solid black arrow, the post-processing step measurement signal 802 from the metrology equipment may be used to extract measurement results from the post-processing physics model 812 of the SOI from the sample. In some implementations, additional data may be used to assist in extracting measurement results from the post-processing physics model 812. For example, as illustrated, the post-processing physics model 812 may receive feed-forward data, e.g., for values ​​of one or more parameters of interest (parameter #1) 825, from the pre-processing physics model 814 and / or from the pre-processing machine learning model 824 to facilitate propagation of information in the pre-processing manufacturing step signal to the post-processing physics model 812. In some implementations, feedback data generated based on the post-processing step measurement signal 802 may be used to assist in extracting measurement results from the post-processing physics model 812. As illustrated, the post-processing physics model 812 may receive feedback data, e.g., initial values ​​of one or more parameters of interest (parameter #2) 823, determined by the post-processing machine learning model 822 based on the post-processing step measurement signal 802 as discussed below. The accuracy of the one or more parameters of interest (parameter #2) 823 benefits from the more accurate one or more parameters of interest (parameter #1) 825 being fed forward to the post-processing physics model 812. In addition, the feedback of the one or more parameters of interest (parameter #2) 823 can break the high correlation of the parameters of interest (e.g., SiGe CD of different etches) that undergo the same manufacturing step.

[0090] The trained post-processing machine learning model 822 is used to predict the final values ​​of one or more parameters of interest (parameter #2) 823 (as well as one or more initial values ​​of one or more parameters of interest (parameter #2) 823, if feedback is used), which may include key parameters, non-key parameters, or both key parameters and non-key parameters. As illustrated by the solid black arrows, the trained post-processing machine learning model 822 uses the post-processing measurements extracted by the post-processing physics model 812 as input features. The trained post-processing machine learning model 822 can also use the post-processing step measurement signal 802 as an input feature. In addition, as illustrated by the gray dashed line, the trained post-processing machine learning model 822 can optionally use the pre-conditioning signal 805 and / or the pre-processing step measurement signal 804 as input features. The final values ​​of one or more parameters of interest can be provided (e.g., reported) to characterize the sample.

[0091] As illustrated, the post-processing physics model 812 (or a separate machine learning model) may be used to predict one or more additional parameters of interest, as illustrated by parameter #3 813, which may include critical parameters, non-critical parameters, or both. By way of example, the post-processing parameters of interest (e.g., parameters #2 and #3) 823 and 813 may be SiGe CD1, SiGe CD2, SiGe CD3, respectively, for a GAA transistor, but other parameters of interest may be determined for a GAA transistor or for other devices being measured. For example, Figure 8 The workflow 800 illustrated in FIG. 8 can also be applied to other pre-processing steps and post-processing steps, such as multiple CD profile measurements in high aspect ratio (HAR) channel hole etching, etc. In addition, additional parameters of interest (parameter #3) 813 can be further fed forward from the post-processing physical model 812 to the post-processing machine learning model 822.

[0092] In some implementations, primary data (e.g., measurement signals used in physical modeling) and auxiliary data (e.g., data used only in machine learning) can originate from different tool groups, or can originate from the same tool group but different data channels, or can originate from the same tool group and the same data channel but different wavelength ranges, time spans, etc. Different data sources can collect data from the same sample site (e.g., on an OCD target or device) of the same wafer, from the same process step, or from different process steps. Different data sources can collect data from different sample sites of the same wafer from the same or different process steps, for example, when the underlying structure has related parameters, so that analyzing the combined data can improve overall performance. As illustrated, at least one physical model can be created to analyze the measurement signals from at least one data source. In addition, if more than one physical model is used, multiple physical models can be optimized independently or jointly, for example, the physical models can be linked so that at least some parameters can be coupled across the physical models, and the combined parameter space can be searched to fit the measurement signals from one or more data sources. The primary data and the auxiliary data may be of different natures, for example, some of the data may be metrology data collected from a tool set, while other data may be sensor data from process equipment, or wafer processing parameters such as gas flow rates, APC parameters, or contextual data such as specific processing tools. In addition, feature engineering and signal preprocessing may be applied before providing data from all sources to a machine learning model for training. Machine learning algorithms may include, for example, but are not limited to, linear regression, neural networks, deep learning, convolutional neural networks (CNNs), ensemble methods, support vector machines (SVMs), random forests, etc., or a combination of multiple models in sequential and / or parallel modes.

[0093] The illustrated workflow effectively combines the use of various measurement techniques and multiple data sources through collaborative physical modeling and machine learning to produce more available information than that provided by a single measurement technique or a single data source. Physical modeling can be performed using previously well-established modeling solutions using the required measurement equipment, and the physical modeling results can be combined with other data that are difficult or impossible to model (called auxiliary data) for machine learning training and prediction. Therefore, the resulting process provides a feasible solution with the advantages of both physical modeling and machine learning, while controlling the computational cost, enabling acceptable TTS for production, and easy to implement and use in practice. In addition, the predictive power can be increased by using data (such as process parameters and sensor data from production equipment), which is combined with metrological data through data mining and data fusion as discussed in this article. The proposed method flexibly adapts to various signals of different properties, while using existing well-developed algorithms to the greatest extent for each type of data source. In addition, the method discussed in this article has a universal application and can be applied to the measurement of any device, OCD or film or other types of targets, for example.

[0094] Fig. 9 An exemplary flow chart depicting an example method 900 for measuring at least one parameter of interest from an SOI according to some implementations is shown. In some implementations, the example method 900 may be implemented by Figure 7 At least one processor of the workflow 700 illustrated in Figure 2 Executed by processor 262 in computing system 260 in the system.

[0095] The at least one processor may obtain a post-processing step measurement signal for the SOI on one or more samples from the metrology device in the post-processing step (902). For example, the component for obtaining the post-processing step measurement signal may be the metrology device 200 and may be connected to the metrology device 200. Figure 2 The post-processing step measurement signal of the SOI on one or more samples in the post-processing step can be, for example, Figure 7 The post-processing step shown measures signal 702 .

[0096] At least one processor may generate a post-processing physical model to extract a post-processing measurement result of the SOI based on a post-processing step measurement signal and at least one of: a first parameter of the SOI in a pre-processing step that is fed forward to the post-processing physical model, a second parameter of the SOI in a post-processing step that is fed back to the post-processing physical model, and a combination thereof (904). For example, the first parameter of the SOI may be determined by at least one of a pre-processing physical model and a pre-processing machine learning model for a pre-processing step measurement signal obtained from the SOI on one or more samples in a pre-processing step. For example, the post-processing measurement result of the SOI may be extracted based on the post-processing step measurement signal and the first parameter or the second parameter, or both the first parameter and the second parameter. In addition, in some specific implementations, one or more first parameters may be used. In some specific implementations, one or more second parameters may be used. The component for generating a post-processing physical model may be a metrology device 200, which includes a computing system 260 configured to generate one or more physical models (models 264pm) through a computer readable program code 266, such as Figure 2 For example, the post-processing physical model can be a first parameter 725 determined using feed-forward parameters from the pre-processing physical model 714 or from the pre-processing physical model 714 and the pre-processing machine learning model 724, or as Figure 7 The post-processing physical model 712 is generated by at least one of the feedbacks of the illustrated second parameter 723. In some implementations, each of the first parameter and the second parameter can be a critical parameter or a non-critical parameter.

[0097] At least one processor may generate a post-processing machine learning model to predict a second parameter of the SOI at the post-processing step, the post-processing machine learning model being generated based on the post-processing measurement results extracted from the post-processing physical model (906). The post-processing machine learning model may also be generated based on the post-processing step measurement signal and the post-processing step data, the post-processing step data including at least one of reference data and experimental design information of the SOI at the post-processing step. For example, the component for generating the post-processing machine learning model may be a metrology device 200, the metrology device including a computing system 260, the computing system being configured to generate and train one or more machine learning models (ML264ml) through computer readable program code 266, such as Figure 2 The post-processing machine learning model may be, for example, a post-processing machine learning model 722 generated based on the post-processing measurement results extracted from the post-processing physical model 712 and the post-processing step measurement signal 702 and the post-processing step data 708.

[0098] The at least one processor may provide parameters for post-processing the physical model and the post-processing machine learning model to measure at least one parameter of interest of the SOI (908). For example, the component for providing parameters for post-processing the physical model and the post-processing machine learning model to measure at least one parameter of interest of the SOI may be the metrology device 200 and the component for providing parameters for post-processing the physical model and the post-processing machine learning model to measure at least one parameter of interest of the SOI. Figure 2 The processor 262 and memory 264 in the computing system 260 shown in FIG. 2 interact.

[0099] In some specific implementations, a post-processing physical model may also be generated based on the post-processing step data, for example, Figure 7 This is illustrated by the arrow from post-processing step data 708 to post-processing physical model 712 shown in FIG.

[0100] In some implementations, the at least one processor may also obtain a pre-processing step measurement signal for the SOI on one or more samples of the pre-processing step from a metrology device, such as Figure 7 The at least one processor may also generate a preprocessing physical model to extract preprocessing measurement results of the SOI based on the preprocessing step measurement signal, for example, Figure 7 The at least one processor may also generate a preprocessing machine learning model to predict a first parameter of the SOI in the preprocessing step, for example, Figure 7 As exemplified by the preprocessing machine learning model 724 shown in . Figure 7 As illustrated by the arrows from the preprocessing physical model 714 to the preprocessing machine learning model 724 and from the preprocessing step data 709 to the preprocessing machine learning model 724, the preprocessing machine learning model can be generated based on the preprocessing measurement results extracted from the preprocessing physical model and the preprocessing step data including at least one of reference data and experimental design information of the SOI in the preprocessing step.

[0101] In some specific implementations, a preprocessing physical model may also be generated based on the preprocessing step data, for example, Figure 7 This is illustrated by the arrow from the pre-processed step data 709 to the pre-processed physical model 714 shown in FIG.

[0102] In some implementations, a post-processing machine learning model may also be generated based on a pre-processing step measurement signal from the SOI in the pre-processing step, for example, Figure 7 This is illustrated by the arrow shown in from the pre-processing step measurement signal 704 to the post-processing machine learning model 722.

[0103] In some implementations, at least one processor may further generate a pre-conditioned signal by combining a pre-processing step measurement signal from the SOI at the pre-processing step with a post-processing step measurement signal from the SOI at the post-processing step, wherein a post-processing machine learning model is also generated based on the pre-conditioned signal, e.g., Figure 7 This is illustrated by the pre-conditioned signal 705 shown in and the arrow from the pre-conditioned signal 705 to the post-processing machine learning model 722.

[0104] In some implementations, at least one processor may also use at least one of a post-processing physical model or a post-processing machine learning model to determine one or more additional parameters of the SOI, e.g., as illustrated by the prediction of parameter #3 713. In some implementations, the one or more additional parameters may include critical parameters, non-critical parameters, or a combination of critical parameters and non-critical parameters.

[0105] Fig.10 An exemplary flow chart depicting an example method 1000 for measuring at least one parameter of interest from an SOI according to some implementations is shown. In some implementations, the example method 1000 may be implemented by Figure 8 At least one processor of the workflow 800 illustrated in Figure 2 Executed by processor 262 in computing system 260 in the system.

[0106] The at least one processor may obtain a post-processing step measurement signal for SOI on one or more samples from a metrology device in a post-processing step (1002). For example, the component for obtaining the post-processing step measurement signal may be the metrology device 200 and may be connected to the metrology device 200. Figure 2 The post-processing step measurement signal of the SOI on one or more samples in the post-processing step can be, for example, Figure 8 The post-processing step shown measures signal 802 .

[0107] The at least one processor may extract post-processing measurement results from the post-processing physical model of the SOI based on the post-processing step measurement signal and at least one of the following: a value of a first parameter of the SOI in the pre-processing step that is fed forward to the post-processing physical model, a value of a second parameter of the SOI in the post-processing step that is fed back to the post-processing physical model, and a combination thereof (1004). For example, the post-processing measurement results of the SOI may be extracted based on the post-processing step measurement signal and the value of the first parameter or the second parameter, or both the first parameter and the second parameter. In addition, in some specific implementations, one or more first parameters may be used. In some specific implementations, one or more second parameters may be used. The component for generating the post-processing measurement results extracted from the post-processing physical model may be a metrology device 200, which includes a computing system 260 configured to generate one or more physical models (models 264pm) through a computer readable program code 266, such as Figure 2 Based on the post-processing step measurement signal 802 and the feed-forward first parameter 825 determined from the pre-processing physical model 814 and the pre-processing machine learning model 824 or as Figure 8 At least one of the illustrated feedback of the second parameter 823 may extract a post-processing measurement result from the post-processing physics model, for example, as illustrated by an arrow from the post-processing physics model 812. In some implementations, each of the first parameter and the second parameter may be a critical parameter or a non-critical parameter.

[0108] The at least one processor may predict a final value of a second parameter of the SOI at the post-processing step from the trained post-processing machine learning model based on the post-processing measurement results extracted from the post-processing physical model (1006). The final value of the second parameter of the SOI may be predicted from the trained post-processing machine learning model further based on the post-processing step measurement signal. For example, the component for predicting the final value of the second parameter of the SOI from the trained post-processing machine learning model may be a metrology device 200, the metrology device including a computing system 260, the computing system being configured to generate and train one or more machine learning models (ML 264ml) via computer readable program code 266, such as Figure 2 The final value of the second parameter of the SOI may be predicted by the trained post-processing machine learning model, for example, as illustrated by parameter #2 823 predicted by the post-processing machine learning model 822 based on the post-processing measurements extracted from the post-processing physics model and the post-processing step measurement signal (e.g., as illustrated by the arrow from the post-processing physics model 812 to the post-processing machine learning model 822 and the arrow from the post-processing step measurement signal 802 to the post-processing machine learning model 822).

[0109] The at least one processor may provide at least a final value for the second parameter of the SOI (1008). For example, the means for providing at least a final value for the second parameter of the SOI may be the metrology device 200 and may be associated with the Figure 2 The computing system 260 and the UI 268 shown in FIG. 2 interact with the processor 262 and the memory 264.

[0110] In some implementations, the value of the first parameter of the SOI can be determined, for example, for a pre-processing step measurement signal obtained from the SOI on one or more samples in the pre-processing step according to at least one of a pre-processing physical model and a trained pre-processing machine learning model. For example, at least one processor can obtain a pre-processing step measurement signal for the SOI on one or more samples in the pre-processing step from a metrology device, for example, as Figure 8 The at least one processor may be configured to measure the signal based on the pre-processing step (e.g., Figure 8 In another example, at least one processor may extract preprocessed measurements of the SOI from the preprocessed physical model based on the preprocessed step measurement signal, and predict the value of the first parameter of the SOI at the preprocessing step from the trained preprocessed machine learning model based on the preprocessed measurements extracted from the preprocessed physical model, for example, as determined by Figure 8 Parameter #1 825 predicted by the pre-processed machine learning model 824 shown in FIG.

[0111] In some implementations, the value of the second parameter of the SOI at the post-processing step can be predicted from a trained post-processing machine learning model based on initial post-processing measurements extracted from the post-processing physics model, e.g., Figure 8 This is illustrated by the arrow from the post-processing physical model 812 to the post-processing machine learning model 822 shown in .

[0112] In some implementations, the final value of the second parameter of the SOI at the post-processing step can also be predicted from the trained post-processing machine learning model based on the pre-processing step measurement signal from the SOI at the pre-processing step, for example, Figure 8 This is illustrated by the arrow shown in from the pre-processing step measurement signal 804 to the post-processing machine learning model 822.

[0113] In some implementations, the at least one processor may further generate a pre-conditioned signal by combining a pre-processing step measurement signal from the SOI at the pre-processing step with a post-processing step measurement signal from the SOI at the post-processing step, wherein a final value of a second parameter of the SOI at the post-processing step is also predicted from the trained post-processing machine learning model based on the pre-conditioned signal, e.g., Figure 8 This is illustrated by the pre-conditioned signal 805 shown in and the arrow from the pre-conditioned signal 805 to the post-processing machine learning model 822.

[0114] In some implementations, at least one processor may also use at least one of a post-processing physical model or a post-processing machine learning model to determine one or more additional parameters of the SOI, such as Figure 8 813. In some implementations, the one or more additional parameters can include critical parameters, non-critical parameters, or a combination of critical parameters and non-critical parameters.

[0115] The above description is intended to be illustrative rather than limiting. For example, the above examples (or one or more aspects thereof) may be used in combination with each other. Other specific implementations may be used, such as those of ordinary skill in the art after reading the above description. In addition, various features may be grouped together, and less than all features of a specific disclosed specific implementation may be used. Therefore, the following aspects are thus incorporated into the above description as examples or specific implementations, wherein each aspect is independently used as a separate specific implementation, and it is contemplated that such specific implementations may be combined with each other in various combinations or permutations. Therefore, the spirit and scope of the appended claims should not be limited to the foregoing description.

Claims

1. A method for measuring at least one parameter of interest from a structure of interest (SOI), the method comprising: obtaining a post-processing step measurement signal for the SOI on the one or more samples from a metrology device during the post-processing step; extracting a post-processing measurement result from a post-processing physical model of the SOI based on the post-processing step measurement signal and at least one of: a value of a first parameter of the SOI fed forward to the post-processing physical model at a pre-processing step, a value of a second parameter of the SOI fed back to the post-processing physical model at the post-processing step, and a combination thereof; predicting, from a trained post-processing machine learning model, a final value of the second parameter of the SOI at the post-processing step based on the post-processing measurements extracted from the post-processing physics model; as well as At least the final value of the second parameter of the SOI is provided.

2. The method of claim 1 , wherein the value of the first parameter of the SOI is determined according to at least one of a preprocessing physical model and a trained preprocessing machine learning model based on a preprocessing step measurement signal obtained from the SOI on the one or more samples in the preprocessing step.

3. The method according to claim 2, further comprising: obtaining, in said pre-processing step, from said metrology device said pre-processing step, said pre-processing step measurement signals for said SOI on said one or more samples; as well as The value of the first parameter is determined from pre-processed measurements of the SOI extracted from the pre-processed physical model based on the pre-processing step measurement signal.

4. The method according to claim 2, further comprising: obtaining, in said pre-processing step, from said metrology device said pre-processing step, said pre-processing step measurement signals for said SOI on said one or more samples; Extracting preprocessed measurement results of the SOI from the preprocessed physical model based on the measurement signal of the preprocessing step; as well as The value of the first parameter of the SOI at the preprocessing step is predicted from the trained preprocessing machine learning model based on the preprocessing measurements extracted from the preprocessing physical model.

5. The method of claim 1 , wherein the value of the second parameter of the SOI at the post-processing step is predicted from the trained post-processing machine learning model based on the post-processing step measurement signal and initial post-processing measurement results extracted from the post-processing physical model.

6. The method of claim 1 , wherein the final value of the second parameter of the SOI at the post-processing step is predicted from the trained post-processing machine learning model also based on a pre-processing step measurement signal from the SOI at the pre-processing step.

7. The method of claim 1 , further comprising generating a pre-conditioning signal by combining a pre-processing step measurement signal from the SOI at the pre-processing step and a post-processing step measurement signal from the SOI at the post-processing step, wherein the final value of the second parameter of the SOI at the post-processing step is also predicted from the trained post-processing machine learning model based on the pre-conditioning signal.

8. The method of claim 1, further comprising determining one or more additional parameters of the SOI using at least one of the post-processing physics model or the trained post-processing machine learning model.

9. A computer system configured to measure at least one parameter of interest from a structure of interest (SOI), the computer system comprising: at least one processor, wherein the at least one processor is configured to: obtaining a post-processing step measurement signal for the SOI on the one or more samples from a metrology device during the post-processing step; extracting a post-processing measurement result from a post-processing physical model of the SOI based on the post-processing step measurement signal and at least one of: a value of a first parameter of the SOI fed forward to the post-processing physical model at a pre-processing step, a value of a second parameter of the SOI fed back to the post-processing physical model at the post-processing step, and a combination thereof; predicting, from a trained post-processing machine learning model, a final value of the second parameter of the SOI at the post-processing step based on the post-processing measurements extracted from the post-processing physics model; as well as At least the final value of the second parameter of the SOI is provided.

10. The computer system of claim 9, wherein the value of the first parameter of the SOI is determined according to at least one of a preprocessing physical model and a trained preprocessing machine learning model based on a preprocessing step measurement signal obtained from the SOI on the one or more samples in the preprocessing step.

11. The computer system of claim 10, wherein the at least one processor is further configured to: obtaining, at the pre-processing step, from the metrology device, the pre-processing step measurement signals for the SOI on the one or more samples; and The value of the first parameter is determined from pre-processed measurements of the SOI extracted from the pre-processed physical model based on the pre-processing step measurement signal.

12. The computer system of claim 10, wherein the at least one processor is further configured to: obtaining, in said pre-processing step, from said metrology device said pre-processing step, said pre-processing step measurement signals for said SOI on said one or more samples; extracting preprocessed measurement results of the SOI from the preprocessed physical model based on the preprocessed step measurement signal; and The value of the first parameter of the SOI at the preprocessing step is predicted from the trained preprocessing machine learning model based on the preprocessing measurements extracted from the preprocessing physical model.

13. The computer system of claim 9, wherein the at least one processor is configured to predict the value of the second parameter of the SOI at the post-processing step from the trained post-processing machine learning model based on the post-processing step measurement signal and initial post-processing measurement results extracted from the post-processing physical model.

14. The computer system of claim 9, wherein the at least one processor is configured to predict the final value of the second parameter of the SOI at the post-processing step from the trained post-processing machine learning model also based on a pre-processing step measurement signal from the SOI at the pre-processing step.

15. The computer system of claim 9, wherein the at least one processor is further configured to generate a pre-conditioning signal by combining a pre-processing step measurement signal from the SOI at the pre-processing step and the post-processing step measurement signal from the SOI at the post-processing step, wherein the at least one processor is configured to predict the final value of the second parameter of the SOI at the post-processing step from the trained post-processing machine learning model also based on the pre-conditioning signal.

16. The computer system of claim 9, wherein the at least one processor is further configured to determine one or more additional parameters of the SOI using at least one of the post-processing physics model or the trained post-processing machine learning model.

17. A system configured to measure at least one parameter of interest from a structure of interest (SOI), the system comprising: means for obtaining, at a post-processing step, a post-processing step measurement signal for the SOI on one or more samples from a metrology device; means for extracting post-processing measurements from a post-processing physical model of the SOI based on the post-processing step measurement signal and at least one of: a value of a first parameter of the SOI fed forward to the post-processing physical model at a pre-processing step, a value of a second parameter of the SOI fed back to the post-processing physical model at the post-processing step, and a combination thereof; means for predicting, from a trained post-processing machine learning model, a final value of the second parameter of the SOI at the post-processing step based on the post-processing measurements extracted from the post-processing physics model; and Means for providing at least the final value of the second parameter of the SOI.

18. The system of claim 17, wherein the value of the first parameter of the SOI is determined according to at least one of a preprocessing physical model and a trained preprocessing machine learning model based on a preprocessing step measurement signal obtained from the SOI on the one or more samples in the preprocessing step.

19. The system of claim 17, wherein the value of the second parameter of the SOI at the post-processing step is predicted from the trained post-processing machine learning model based on the post-processing step measurement signal and initial post-processing measurement results extracted from the post-processing physical model.

20. The system of claim 17, wherein the final value of the second parameter of the SOI at the post-processing step is predicted from the trained post-processing machine learning model based also on a pre-processing step measurement signal from the SOI at the pre-processing step.

21. The system of claim 17, wherein the value of the second parameter of the SOI at the post-processing step is predicted from the trained post-processing machine learning model based on the post-processing step measurement signal and initial post-processing measurement results extracted from the post-processing physical model.

22. The system of claim 17, wherein the final value of the second parameter of the SOI at the post-processing step is predicted from the trained post-processing machine learning model also based on a pre-processing step measurement signal from the SOI at the pre-processing step.

23. The system of claim 17, further comprising means for generating a pre-conditioning signal by combining a pre-processing step measurement signal from the SOI at the pre-processing step and a post-processing step measurement signal from the SOI at the post-processing step, wherein the final value of the second parameter of the SOI at the post-processing step is also predicted from the trained post-processing machine learning model based on the pre-conditioning signal.

24. The system of claim 17, further comprising means for determining one or more additional parameters of the SOI using at least one of the post-processing physics model or the trained post-processing machine learning model.

Images