Determining substrate profile characteristics using machine learning

Abstract

Spectral data associated with the first prior substrate and / or the second prior substrate is acquired. Metrology measurements associated with a first portion of the first prior substrate are determined based on one or more metrology measurements taken on at least one of the second portion of the first prior substrate or the third portion of the second prior substrate. Training data is generated for training a machine learning model to predict metrology measurements of the current substrate. Generating the training data includes generating a first training input including the spectral data associated with the first prior substrate and generating a first target output for the first training input, the first target output including the determined metrology measurements associated with the first portion of the first prior substrate. The training data is provided for training the machine learning model.

Description

[Technical Field]

[0001] FIELD Embodiments of the present disclosure relate generally to manufacturing systems and, more particularly, to determining profile characteristics of a substrate. [Background technology]

[0002] Substrate profile characteristics are metrics that can be used to evaluate a substrate during or after processing in a manufacturing system. Typically, substrate profile characteristics are measured using a metrology system that is separate from the manufacturing tool used in the manufacturing system. To measure the substrate profile characteristics, the substrate is removed from the manufacturing tool and measured with the metrology system. After measurements for the substrate are obtained with the metrology system, the substrate is returned to the manufacturing tool for further processing. Removing the substrate from the manufacturing tool and measuring it with the metrology system is a costly operation that reduces overall process efficiency. The cost of removing the substrate from the manufacturing tool reduces the sampling rate of all substrates processed in the manufacturing system because few substrates processed in the manufacturing system are measured. Measurements generated for these few substrates are used to make process decisions for other substrates processed in the manufacturing tool that are not measured. Process decisions made based on measurements generated for a few substrates can result in substrate defects and, in some cases, damage to manufacturing system equipment. Summary of the Invention

[0003] Some of the described embodiments include a method for training a machine learning model to predict metrology measurements of a current substrate being processed in a manufacturing system. The method includes acquiring spectral data associated with a first portion of a first prior substrate in the manufacturing system and at least one of a second portion of the first prior substrate or a third portion of a second prior substrate in the manufacturing system. The method further includes identifying one or more metrology measurements acquired for at least one of the second portion of the first prior substrate or the third portion of the second prior substrate. The method further includes determining metrology measurements associated with the first portion of the first prior substrate based on the identified one or more metrology measurements. The method further includes generating training data for training the machine learning model to predict metrology measurements of a current substrate in the manufacturing system. Generating the training data includes generating a first training input including spectral data associated with the first portion of the first prior substrate and generating a first target output for the first training input, the first target output including the determined metrology measurements associated with the first portion of the first prior substrate. The method further includes providing data for training the machine learning model with respect to (i) a set of training inputs including the first training input, and (ii) a set of target outputs including the first target output.

[0004] In some embodiments, an apparatus includes a memory and a processing device coupled to the memory. The processing device is for performing operations including acquiring spectral data associated with a first portion of a first prior substrate in a manufacturing system and at least one of a second portion of the first prior substrate or a third portion of a second prior substrate in the manufacturing system. The operations further include identifying one or more metrology measurements acquired for at least one of the second portion of the first prior substrate or the third portion of the second prior substrate. The operations further include determining metrology measurements associated with the first portion of the first prior substrate based on the identified one or more metrology measurements. The operations further include generating training data for training a machine learning model to predict metrology measurements of a current substrate in the manufacturing system. Generating the training data includes generating a first training input including spectral data associated with the first portion of the first prior substrate and generating a first target output for the first training input, the first target output including the determined metrology measurements associated with the first portion of the first prior substrate. The operations further include providing data to train the machine learning model with respect to (i) a set of training inputs including the first training input, and (ii) a set of target outputs including the first target output.

[0005] In some embodiments, a non-transitory computer-readable storage medium includes instructions that, when executed by a processing device, cause the processing device to perform operations, the operations including acquiring spectral data associated with a first portion of a first prior substrate in a manufacturing system and at least one of a second portion of the first prior substrate or a third portion of a second prior substrate in the manufacturing system. The operations further include identifying one or more metrology measurements acquired for at least one of the second portion of the first prior substrate or the third portion of the second prior substrate. The operations further include determining metrology measurements associated with the first portion of the first prior substrate based on the identified one or more metrology measurements. The operations further include generating training data for training a machine learning model to predict metrology measurements of a current substrate in the manufacturing system. Generating the training data includes generating a first training input including spectral data associated with the first portion of the first prior substrate and generating a first target output for the first training input, the first target output including the determined metrology measurements associated with the first portion of the first prior substrate. The operations further include providing data to train the machine learning model with respect to (i) a set of training inputs including the first training input, and (ii) a set of target outputs including the first target output.

[0006] The present disclosure is illustrated by way of example, and not limitation, in the accompanying drawings, in which like reference numerals indicate similar elements. It should be noted that different references to "an" or "one" embodiment in the present disclosure are not necessarily to the same embodiment, and such references mean at least one. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 illustrates an exemplary computer system architecture according to aspects of the present disclosure. [Figure 2]1 is a flowchart of a method for training a machine learning model according to an aspect of the present disclosure. [Figure 3] FIG. 1 is a schematic top view of an exemplary manufacturing system according to aspects of the present disclosure. [Figure 4] 1 is a schematic cross-sectional side view of a substrate measurement subsystem according to an aspect of the present disclosure. [Figure 5] FIG. 1 illustrates spectral data collected on a substrate, according to aspects of the present disclosure. [Figure 6] 1 is a flowchart of a method for estimating metrology values ​​for a profile of a substrate using a machine learning model, according to an aspect of the present disclosure. [Figure 7A-7C] FIG. 10 illustrates an exemplary GUI that provides a display of estimated measurements of a profile of a substrate, according to aspects of the present disclosure. [Figure 8] 1 is a flowchart of a method for generating training data for training a machine learning model, according to an aspect of the present disclosure. [Figure 9] 1 illustrates an example of determining metrology measurements for a substrate, according to aspects of the present disclosure. [Figure 10] 1 is a flowchart of a method for determining metrology measurements for a substrate in a manufacturing system, according to an aspect of the present disclosure. [Figure 11] 10 is a flowchart of another method for determining metrology measurements for a substrate in a manufacturing system in accordance with aspects of the present disclosure. [Figure 12] FIG. 1 is a block diagram of an exemplary computer system that operates in accordance with one or more aspects of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0008] Characteristics of a substrate profile (e.g., a surface containing three-dimensional (3D) structures, a surface containing non-3D structures, etc.) are important to the overall performance of the final processed substrate and / or the overall production yield of the substrate in a manufacturing system. In some cases, characteristics of the substrate profile can be monitored by generating metrology measurements on the substrate during or after substrate processing in a manufacturing system. Metrology measurements can include etch rate (i.e., the rate at which a particular material deposited on the surface of the substrate is etched in a processing chamber), etch rate uniformity (i.e., the variation in etch rate across two or more portions of the surface of the substrate), critical dimension (i.e., a unit of measure for measuring the dimensions of an element of the substrate, such as a line, column, opening, space, etc.), critical dimension uniformity (i.e., the variation in critical dimension across the surface of the substrate), edge-to-edge placement error (EPE) (i.e., the difference between an intended feature and a resulting feature contained on the surface of the substrate), etc.

[0009] The implementations described herein provide methods and systems for training and using machine learning models to predict metrology measurements for current substrates being processed in a manufacturing system. The machine learning models can be trained using historical spectral data collected for various portions of previous substrates processed in the manufacturing system. The spectral data can correspond to the intensity of the detected wave of energy (i.e., the intensity of the amount of energy) for each given wavelength of the detected wave of energy. In some embodiments, the spectral data can be generated by a substrate measurement subsystem included in the measurement system. In other or similar embodiments, the spectral data can be generated in another portion of the manufacturing system, such as a processing chamber. The historical spectral data can be provided as training input for the machine learning model. The machine learning can also be trained using historical non-spectral data collected for various portions of previous substrates. For example, eddy current data, capacitance data, etc. can be generated for a substrate and provided as training input for the machine learning model.

[0010] In some embodiments, the machine learning model can be further trained using historical spectral data that indicates a previous portion of the substrate associated with the historical spectral data. The position data can refer to the position and / or orientation of the substrate when the spectral data for the portion of the substrate was measured (i.e., in the substrate measurement subsystem or in the processing chamber). In some embodiments, the historical position data can also be provided as training input for the machine learning model.

[0011] The machine learning model can be further trained using historical metrology measurements collected for previous substrates processed in the manufacturing system. In some embodiments, the historical metrology measurements can be received from a metrology measurement system separate from the manufacturing system (referred to as an external metrology measurement system). In other or similar embodiments, the historical metrology measurements can be received from a client device of the manufacturing system. The historical metrology measurements can be generated for each substrate processed in the manufacturing system. The historical metrology measurements can be provided as a target output for the machine learning model.

[0012] In some embodiments, training data used to train a machine learning model can be generated based on predicted or otherwise determined metrology measurements for prior substrates in a manufacturing system. In one example, spectral data can be collected for a first portion of a first prior substrate in a manufacturing system according to embodiments described herein. Spectral data can also be collected for a second portion of the first prior substrate and / or a third portion of a second prior substrate in a manufacturing system. In some embodiments, metrology measurements can be collected for the second portion of the first prior substrate and / or the third portion of the second prior substrate (e.g., not for the first portion of the first prior substrate). Representations of coordinates (e.g., Cartesian coordinates, etc.) of the first portion of the first prior substrate and the second portion of the first prior substrate and / or the third portion of the second prior substrate can be provided as inputs to the function. Metrology measurements measured for the second portion of the first prior substrate and / or the third portion of the second prior substrate can also be provided as inputs to the function. In some embodiments, the function can include a linear interpolation function, an extrapolation function, a nearest neighbor interpolation function, or a Euclidean distance function. The function may provide as an output an indication of one or more metrology measurements of the substrate. A metrology measurement for a first portion of the first substrate may be determined based on the one or more outputs of the function.

[0013] In additional or alternative embodiments, the spectral data collected for the first portion can be provided as input to an additional machine learning model. In some embodiments, the spectral data can be provided along with context data associated with the first prior substrate. The additional machine learning model can be trained to predict one or more metrology measurements for the prior substrate based on the spectral data and context data for the prior substrate in the manufacturing system. The context data can include an indication of a first coordinate associated with the first portion of the first prior substrate, a substrate process performed for the first prior substrate, a period during which the substrate process was performed for the first prior substrate, a period during which the spectral data was collected for the first prior substrate, an indication of one or more types of equipment used to perform the substrate process, etc. One or more outputs of the additional machine learning model can include metrology data including one or more sets of metrology measurements and an indication of a confidence level that each set of metrology measurements corresponds to the first portion of the first prior substrate. A set of metrology measurements having a confidence level that meets a confidence criterion (e.g., exceeds a threshold confidence level) is identified. The set of metrology measurements can include metrology measurements for the first portion of the first prior substrate. Further details regarding predicting or otherwise determining metrology measurements for prior substrates in a manufacturing system are provided herein.

[0014] Once the machine learning model is trained, it can be used to predict metrology measurements for a current substrate being processed in the manufacturing system. Spectral data can be generated for the current substrate (i.e., in the substrate measurement subsystem or processing chamber) during or after substrate processing in the manufacturing system. The spectral data can be provided as input to the trained machine learning model. In some embodiments, positional data can also be generated for the current substrate, and the positional data is associated with the spectral data. In such embodiments, the positional data can be provided as a separate input to the trained machine learning model along with the spectral data. The trained machine learning model can generate one or more outputs including metrology measurements for previous substrates processed in the manufacturing system and a confidence that the current substrate being processed in the manufacturing system is associated with the metrology measurements for the previous substrate. Metrology measurements for the current substrate being processed in the manufacturing system can be extracted from the one or more outputs. In some embodiments, the metrology measurements for the current substrate can be provided to a user of the manufacturing system via a graphical user interface (GUI) displayed on a client device of the manufacturing system.

[0015] Aspects of the present disclosure address the above-described shortcomings of the prior art by providing systems and methods for training and using machine learning models to predict metrology measurements for substrates being processed in a manufacturing system. Spectral and / or non-spectral data can be generated for each substrate in various parts of the manufacturing system (i.e., substrate measurement subsystem, processing chamber, etc.) and provided to a trained machine learning model to determine metrology measurements for the substrate while it remains in the manufacturing system. By determining metrology measurements for the substrate while it remains in the manufacturing system, the substrate is not removed from the manufacturing system during substrate processing, thereby improving overall system throughput. Furthermore, because spectral data and / or spectra can be generated for each substrate being processed in the manufacturing system, metrology measurements can be generated for each substrate, increasing the sampling rate for all substrates processed in the manufacturing system. Process corrections for a substrate can be made in the manufacturing system based on the metrology measurements for that substrate rather than based on metrology measurements for another substrate, increasing the likelihood that the process correction will result in successful processing of the substrate. As a result, fewer defects are generated in the manufacturing system, thereby improving overall system efficiency. Additionally, deviations from expected metrology measurements for the substrate can be detected, and based on the detected deviations, error protocols (e.g., sending an error message to an operator of the manufacturing system, stopping operation of the manufacturing system, etc.) can be initiated to prevent unnecessary damage to the substrate and / or the manufacturing system.

[0016] FIG. 1 illustrates an exemplary computer system architecture 100 according to aspects of the present disclosure. In some embodiments, the computer system architecture 100 may be included as part of a manufacturing system for processing substrates, such as the manufacturing system 300 of FIG. 3 . The computer system architecture 100 includes a client device 120, manufacturing equipment 124, metrology equipment 128, a prediction server 112 (e.g., for generating prediction data, providing model adaptation, using a knowledge base, etc.), and a data store 140. The prediction server 112 may be part of a prediction system 110. The prediction system 110 may further include server machines 170, 180. The manufacturing equipment 124 may include a sensor 125 configured to capture data about substrates being processed in the manufacturing system. In some embodiments, the manufacturing equipment 124 and the sensor 126 may be part of a sensor system including a sensor server (e.g., a field service server (FSS) at the manufacturing facility) and a sensor identifier reader (e.g., a front-opening unified pod (FOUP) radio frequency identification (RFID) reader at the sensor system). In some embodiments, the metrology device 128 may be part of a metrology system that includes a metrology server (eg, metrology database, metrology folder, etc.) and a metrology identifier reader (eg, a FOUP RFID reader in the metrology system).

[0017] The manufacturing equipment 124 may manufacture products according to a recipe or in continuous operation over a period of time. The manufacturing equipment 124 may include a substrate measurement subsystem including one or more sensors 126 configured to generate spectral and / or positional data about the substrate embedded within the substrate measurement subsystem. The sensors 126 configured to generate spectral data (referred to herein as spectral sensing components) may include reflectometry sensors, ellipsometry sensors, thermal spectral sensors, capacitive sensors, etc. In some embodiments, the spectral sensing components may be included within the substrate measurement subsystem or another portion of the manufacturing system. The one or more sensors 126 (e.g., eddy current sensors, etc.) may also be configured to generate non-spectral data about the substrate. Further details regarding the manufacturing equipment 124 and the substrate measurement subsystem are provided with respect to FIGS. 3 and 4.

[0018] In some embodiments, the sensors 126 can provide sensor data associated with the manufacturing equipment 124. The sensor data can include one or more values ​​of temperature (e.g., heater temperature), spacing (SP), pressure, high frequency radio frequency (HFRF), electrostatic chuck (ESC) voltage, current, flow, power, voltage, etc. The sensor data can be associated with or indicative of hardware parameters, such as settings or components (e.g., size, type, etc.) of the manufacturing equipment 124, or manufacturing parameters, such as process parameters of the manufacturing equipment 124. The sensor data can be provided while the manufacturing equipment 124 is performing a manufacturing process (e.g., equipment readings as the product is processed). The sensor data 142 can vary from substrate to substrate.

[0019] The metrology equipment 128 can provide metrology data associated with substrates (e.g., wafers, etc.) processed by the manufacturing equipment 124. The metrology data can include one or more values ​​of film property data (e.g., wafer-space film properties), dimensions (e.g., thickness, height, etc.), dielectric constant, dopant concentration, density, defects, etc. In some embodiments, the metrology data can further include values ​​of one or more surface profile property data (e.g., etch rate, etch rate uniformity, critical dimension, critical dimension uniformity across the surface of the substrate, edge placement error, etc.) of one or more features included in the surface of the substrate. The metrology data can be for finished or semi-finished products. The metrology data can vary from substrate to substrate.

[0020] The client device 120 may include computing devices such as a personal computer (PC), a laptop, a mobile phone, a smartphone, a tablet computer, a netbook computer, a network-connected television ("smart TV"), a network-connected media player (e.g., a Blu-ray player), a set-top box, an over-the-top (OTT) streaming device, an operator box, etc.

[0021] In some embodiments, metrology data may be received from a client device 120. The client device 120 may display a graphical user interface (GUI) that allows a user to provide as input metrology measurements for substrates processed in the manufacturing system.

[0022] Data store 140 may be memory (e.g., random access memory), a drive (e.g., hard drive, flash drive), a database system, or another type of component or device capable of storing data. Data store 140 may include multiple storage components (e.g., multiple drives or multiple databases) that may span multiple computing devices (e.g., multiple server computers). Data store 140 may store spectral data, non-spectral data, measurement data, and prediction data. The spectral data may include historical spectral data (e.g., spectral data generated for previous substrates processed in the manufacturing system) and / or current spectra (e.g., spectral data generated for the current substrate being processed in the manufacturing system. The current spectral data may be data from which predicted data is generated. It should be noted that while embodiments of the present disclosure refer to spectral data for training machine learning models, embodiments of the present disclosure may also include non-spectral data used to train machine learning models. In some embodiments, the metrology data may include historical metrology data (e.g., metrology measurements for previous substrates processed in the manufacturing system). The data store 140 may also store contextual data associated with substrates being processed in the manufacturing system (e.g., recipe name, recipe step number, preventive maintenance indicator, operator, etc.).

[0023] In some embodiments, data store 140 may be configured to store data that is inaccessible to users of the manufacturing system. For example, spectral data, non-spectral data, and / or location data acquired for substrates being processed in the manufacturing system may be inaccessible to users of the manufacturing system. In some embodiments, all data stored in data store 140 may be inaccessible to users (e.g., operators) of the manufacturing system. In other or similar embodiments, some of the data stored in data store 140 may be inaccessible to users, while other portions of the data stored in data store 140 may be accessible to users. In some embodiments, one or more portions of the data stored in data store 140 may be encrypted using an encryption mechanism unknown to the users (e.g., the data is encrypted using a private encryption key). In other or similar embodiments, data store 140 may include multiple data stores, where data inaccessible to users is stored in one or more first data stores and data accessible to users is stored in one or more second data stores.

[0024] In some embodiments, prediction system 110 includes server machine 170 and server machine 180. Server machine 170 includes training set generator 172 that can generate training data sets (e.g., a set of data inputs and a set of target outputs) for training, validating, and / or testing machine learning model 190. Some operations of training set generator 172 are described in detail below with respect to FIGS. 2 and 8-11. In some embodiments, training set generator 172 can divide training data into a training set, a validation set, and a test set. In some embodiments, prediction system 110 generates multiple sets of training data. For example, a first set of training data can correspond to a first type of spectral data (e.g., reflectometry spectral data), and a second set of training data can correspond to a second type of spectral data (e.g., ellipsometry spectral data).

[0025] The server machine 180 may include a training engine 182, a validation engine 184, a selection engine 185, and / or a test engine 186. An engine may refer to hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, a processing device, etc.), software (e.g., instructions running on a processing device, a general-purpose computer system, or a dedicated machine), firmware, microcode, or a combination thereof. The training engine 182 may be capable of training a machine learning model 190. The machine learning model 190 may refer to a model artifact created by the training engine 182 using training data including training inputs and corresponding target outputs (correct answers for each training input). The training engine 182 may find patterns in the training data that map the training inputs to target outputs (predicted answers) and provide a machine learning model 190 that incorporates these patterns. The machine learning model 190 may use one or more of a support vector machine (SVM), a radial basis function (RBF), clustering, supervised machine learning, semi-supervised machine learning, unsupervised machine learning, a k-nearest neighbor algorithm (k-NN), linear regression, random forests, a neural network (e.g., an artificial neural network), and the like.

[0026] The validation engine 184 may be capable of validating the trained machine learning models 190 using the corresponding set of features of the validation set by the training set generator 172. The validation engine 184 may determine the accuracy of each of the trained machine learning models 190 based on the corresponding set of features of the validation set. The validation engine 184 may discard trained machine learning models 190 that have an accuracy that does not meet a threshold accuracy. In some embodiments, the selection engine 185 may be capable of selecting a trained machine learning model 190 that has an accuracy that meets the threshold accuracy. In some embodiments, the selection engine 185 may be capable of selecting the trained machine learning model 190 with the highest accuracy of the trained machine learning models 190.

[0027] The testing engine 186 may be capable of testing the trained machine learning models 190 using the corresponding set of features of the test set by the training set generator 172. For example, a first trained machine learning model 190 trained using a first set of features of the training set may be tested using a first set of features of the test set. The testing engine 186 may determine the trained machine learning model 190 that has the highest accuracy of all of the trained machine learning models based on the test set.

[0028] The prediction server 112 includes a prediction component 114 that can provide spectral and / or non-spectral data for a portion of a current substrate being processed in the manufacturing system as input to a trained machine learning model 190 and run the trained machine learning model 190 on the input to obtain one or more outputs. As described in more detail below with respect to FIG. 4 , in some embodiments, the prediction component 114 can also extract data from the output of the trained machine learning model 190 and use the confidence data to estimate metrology measurements for the portion of the substrate.

[0029] The confidence data can include or indicate a confidence that the measurement value corresponds to one or more properties of the current spectral data and / or the substrate associated with the spectral data. In one example, the confidence is a real number between 0 and 1, where 0 indicates no confidence that the measurement value corresponds to one or more properties of the substrate associated with the current spectral data and 1 indicates absolute confidence that the measurement value corresponds to one or more properties of the substrate associated with the current spectral data. In some embodiments, instead of determining measurements measured using the metrology instrument 128, the system 100 can use the prediction system 110 to determine measurements for substrates being processed in the manufacturing system.

[0030] Client devices 120, manufacturing equipment 124, sensors 126, measurement equipment 128, prediction server 112, data store 140, server machine 170, and server machine 180 may be coupled to each other via network 130. In some embodiments, network 130 is a public network that provides client devices 120 with access to prediction server 112, data store 140, and other publicly available computing devices. In some embodiments, network 130 is a private network that provides client devices 120 with access to manufacturing equipment 124, measurement equipment 128, data store 140, and other privately available computing devices. Network 130 may include one or more wide area networks (WANs), local area networks (LANs), wired networks (e.g., Ethernet networks), wireless networks (e.g., 802.11 networks or Wi-Fi networks), cellular networks (e.g., Long Term Evolution (LTE) networks), routers, hubs, switches, server computers, cloud computing networks, and / or combinations thereof.

[0031] It should be noted that in some other implementations, the functionality of server machines 170, 180 and prediction server 112 may be provided by fewer machines. For example, in some embodiments, server machines 170, 180 may be combined into a single machine, and in some other or similar embodiments, server machines 170, 180 and prediction server 112 may be combined into a single machine.

[0032] In general, functions described in one implementation as being performed by server machine 170, server machine 180, and / or prediction server 112 may also be performed by client device 120. Additionally, functions attributed to particular components may be performed by different or multiple components acting together.

[0033] In embodiments, a "user" may be represented as a single individual. However, other embodiments of the present disclosure encompass a "user" being an entity controlled by multiple users and / or automated sources. For example, a set of individual users federated as a group of administrators may be considered a "user."

[0034] 2 is a flowchart of a method 200 for training a machine learning model according to an embodiment of the present disclosure. Method 200 is performed by processing logic, which may include hardware (e.g., circuitry, dedicated logic), software (e.g., running on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In one implementation, method 200 may be performed by a computer system such as computer system architecture 100 of FIG. 1. In other or similar implementations, one or more operations of method 200 may be performed by one or more other machines not shown. In some embodiments, one or more operations of method 200 may be performed by training set generator 172 of server machine 170.

[0035] For ease of explanation, the methods are illustrated and described as a series of acts. However, acts in accordance with the present disclosure can be performed in various orders and / or simultaneously, as well as with other acts not presented and described herein. Moreover, not all illustrated acts may be performed to implement a method in accordance with the disclosed subject matter. In addition, those skilled in the art will understand and appreciate that a method can alternatively be represented as a series of interrelated states via a state diagram or events. In addition, it should be understood that the methods disclosed herein can be stored on an article of manufacture to facilitate transferring and transporting such methodologies to a computing device. As used herein, the term article of manufacture is intended to encompass a computer program accessible from any computer-readable device or storage medium.

[0036] At block 210, processing logic initializes a training set T to an empty set (e.g., {}). At block 220, processing logic receives data (e.g., spectral data, non-spectral data, etc.) about substrates being processed in the manufacturing system. In some embodiments, the data may be received from a substrate metrology subsystem integrated into the manufacturing system. In other or similar embodiments, the data may be received from one or more sensors in another part of the manufacturing system (e.g., a processing chamber, a load lock, a transfer chamber, etc.). Note that in some other implementations, the data may be received in some other manner and may not be received from a part of the manufacturing system.

[0037] At block 230, processing logic may receive position data for a substrate being processed in the manufacturing system. In some embodiments, the position data may be received from the substrate measurement subsystem along with the data. In other or similar embodiments, the data may be received from one or more sensors in another part of the manufacturing system. Note that in some other implementations, the position data may be received in some other manner and may not be received from part of the manufacturing system.

[0038] At block 240, processing logic receives one or more metrology measurements for the substrate. The metrology measurements for the substrate may be obtained by a metrology measurement system separate from the manufacturing system (i.e., an external metrology measurement system). In some embodiments, the external metrology measurement system may be communicatively coupled to the manufacturing system (e.g., by network 130 of FIG. 1 ). In such embodiments, processing logic may receive the one or more metrology measurements for the substrate from the external metrology measurement system over the network. In other embodiments, the metrology measurements may be generated by the external metrology measurement system and provided to the manufacturing system via a client device. For example, a client device connected to the manufacturing system may provide a graphical user interface (GUI) to a user (e.g., an operator) of the manufacturing system. After the substrate is measured by the external metrology subsystem, the user may provide the metrology measurements to the client device via the GUI. In response to receiving the provided metrology measurements, the client device may store the metrology measurements in a data store, such as data store 140 of the manufacturing system.

[0039] In some embodiments, the processing logic may determine metrology measurements for a portion of a substrate in the manufacturing system based on metrology measurements collected for other portions of the substrate and / or other substrates. Further details regarding determining such metrology measurements and using such metrology measurements to generate training data are provided below with respect to Figures 8-11.

[0040] At block 250, processing logic generates an input / output mapping. The input / output mapping refers to training inputs that include or are based on data about the substrate, and target outputs for the training inputs, where the target outputs identify metrology measurements for the substrate, and the training inputs are associated with (or mapped to) the target outputs. At block 260, processing logic adds the input / output mapping to a training set T.

[0041] At block 270, processing logic determines whether training set T includes a sufficient amount of training data to train the machine learning model. Note that in some implementations, the sufficiency of training set T may be determined solely based on the number of input / output mappings in the training set, while in some other implementations, the sufficiency of training set T may be determined based on one or more other criteria (e.g., a measure of diversity of training examples, etc.) in addition to or instead of the number of input / output mappings. In response to determining that training set T includes a sufficient amount of training data to train the machine learning model, processing logic provides training set T for training the machine learning model. In response to determining that the training set does not include a sufficient amount of training data to train the machine learning model, method 200 returns to block 220.

[0042] At block 280, processing logic provides a training set T for training the machine learning model. In one implementation, the training set T is provided to the training engine 182 of the server machine 180 for training. In the case of a neural network, for example, input values ​​of a given input / output mapping (e.g., spectral data for a previous substrate) are input to the neural network, and output values ​​of the input / output mapping are stored in output nodes of the neural network. The connection weights of the neural network are then adjusted according to a learning algorithm (e.g., backpropagation, etc.), and the procedure is repeated for other input / output mappings of the training set T. After block 280, the machine learning model 190 can be used to predict measurements for future substrates processed in the manufacturing system (e.g., according to method 600 of FIG. 6, described below).

[0043] 3 is a schematic top view of an exemplary manufacturing system 300 according to an embodiment of the present disclosure. The manufacturing system 300 is capable of performing one or more processes on a substrate 302. The substrate 302 may be any suitable rigid, fixed-dimensional, planar article suitable for fabricating electronic devices or circuit components thereon, such as, for example, a silicon-containing disk or wafer, a patterned wafer, a glass plate, or the like.

[0044] The manufacturing system 300 may include a process tool 304 and a factory interface 306 coupled to the process tool 304. The process tool 304 may include a housing 308 having a transfer chamber 310 therein. The transfer chamber 310 may include one or more processing chambers (also referred to as process chambers) 314, 316, and 318 arranged around and coupled to the transfer chamber 310. The processing chambers 314, 316, and 318 may be coupled to the transfer chamber 310 through respective ports, such as slit valves. The transfer chamber 310 may also include a transfer chamber robot 312 configured to transfer the substrate 302 between the process chambers 314, 316, and 318, the load lock 320, and the like. The transfer chamber robot 312 may include one or more arms, each including one or more end effectors at the end of each arm. The end effectors may be configured to handle specific objects, such as wafers.

[0045] The processing chambers 314, 316, 318 may be configured to perform any number of processes on the substrate 302. The same or different substrate processes may be performed in each processing chamber 314, 316, 318. The substrate processes may include atomic layer deposition (ALD), physical vapor deposition (PVD), chemical vapor deposition (CVD), etching, annealing, hardening, pre-cleaning, metal or metal oxide removal, etc. In some embodiments, the substrate processes may include a combination of two or more of atomic layer deposition (ALD), physical vapor deposition (PVD), chemical vapor deposition (CVD), etching, annealing, hardening, pre-cleaning, metal or metal oxide removal, etc. Other processes may also be performed on the substrate. The processing chambers 314, 316, 318 each may include one or more sensors configured to capture data about the substrate 302 and / or the environment within the processing chambers 314, 316, 318 before, after, or during substrate processing. In some embodiments, one or more sensors may be configured to capture spectral and / or non-spectral data about a portion of the substrate 302 .

[0046] A load lock 320 may also be coupled to the housing 308 and the transfer chamber 310. The load lock 320 may be configured to interface with and be coupled to one side of the transfer chamber 310 and to the factory interface 306. In some embodiments, the load lock 320 may have an environmentally controlled atmosphere that can be changed from a vacuum environment (where substrates may be transferred to and from the transfer chamber 310) to an inert gas environment at or near atmospheric pressure (where substrates may be transferred to and from the factory interface 306).

[0047] The factory interface 306 may be any suitable enclosure, such as, for example, a front-end equipment module (EFEM). The factory interface 306 may be configured to receive substrates 302 from substrate carriers 322 (e.g., front-opening unified pods (FOUPs)) docked to various load ports 324 of the factory interface 306. A factory interface robot 326 (shown in dotted lines) may be configured to transfer substrates 302 between the substrate carriers (also referred to as containers) 322 and the load locks 320. In other and / or similar embodiments, the factory interface 306 may be configured to receive replacement parts from a replacement parts storage container 322.

[0048] The manufacturing system 300 may also be connected to a client device (not shown) configured to provide information to a user (e.g., an operator) regarding the manufacturing system 300. In some embodiments, the client device may provide information to a user of the manufacturing system 300 via one or more graphical user interfaces (GUIs). For example, the client device may provide information regarding one or more modifications to be made to a process recipe for the substrate 302 via the GUI.

[0049] The manufacturing system 300 may also include a system controller 328. The system controller 328 may be and / or include a computing device such as a personal computer, a server computer, a programmable logic controller (PLC), a microcontroller, etc. The system controller 328 may include one or more processing devices, which may be a general-purpose processing device such as a microprocessor, a central processing unit, etc. More specifically, the processing device may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or a processor implementing other instruction sets or combinations of instruction sets. The processing device may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), a network processor, etc. The system controller 328 may include a data storage device (e.g., one or more disk drives and / or solid-state drives), a main memory, a static memory, a network interface, and / or other components. The system controller 328 may execute instructions to perform any one or more of the methods and / or embodiments described herein. In some embodiments, the system controller 328 may execute instructions to perform one or more operations in the manufacturing system 300 according to a process recipe. The instructions may be stored (during execution of the instructions) in a computer-readable storage medium, which may include a main memory, a static memory, a secondary storage, and / or a processing device.

[0050] The system controller 328 can receive data from sensors contained on or within various portions of the manufacturing system 300 (e.g., processing chambers 314, 316, 318, transfer chamber 310, load lock 320, etc.). The data received by the system controller 328 can include spectral and / or non-spectral data about portions of the substrate 302. For purposes of this description, the system controller 328 is described as receiving data from sensors contained within the processing chambers 314, 316, 318. However, the system controller 328 can receive data from any portion of the manufacturing system 300 and use the data received from that portion in accordance with the embodiments described herein. In an illustrative example, the system controller 328 can receive spectral data from one or more sensors in the processing chambers 314, 316, 318 before, after, or during substrate processing in the processing chambers 314, 316, 318. The data received from sensors in various portions of the manufacturing system 300 can be stored in a data store 350. Data store 350 may be included as a component within system controller 328 or may be a separate component from system controller 328. In some embodiments, data store 350 may be data store 140 described with respect to FIG.

[0051] The manufacturing system 300 may further include a substrate measurement subsystem 340. The substrate measurement subsystem 340 may obtain spectral measurements for one or more portions of the substrate 302 before or after the substrate 302 is processed in the manufacturing system 300. In some embodiments, the substrate measurement subsystem 340 may obtain spectral measurements for one or more portions of the substrate 302 in response to receiving a request for spectral measurements from the system controller 328. The substrate measurement subsystem 340 may be integrated within a portion of the manufacturing system 300. In some embodiments, the substrate measurement subsystem 340 may be integrated within the factory interface 306. In other or similar embodiments, the substrate measurement subsystem 340 may not be integrated into any portion of the manufacturing system 300, but may instead be a stand-alone component. In such embodiments, the substrate 302 measured by the substrate measurement subsystem 340 may be transferred to or from a portion of the manufacturing system 300 before or after the substrate 302 is processed in the manufacturing system 300.

[0052] The substrate measurement subsystem 340 may obtain spectral measurements for a portion of the substrate 302 by generating spectral data and / or a spectrum for the portion of the substrate 302. In some embodiments, the substrate measurement subsystem 340 is configured to generate spectral data, non-spectral data, positional data, and other substrate characteristic data (e.g., thickness of the substrate 302, width of the substrate 302, etc.) for the substrate 302. After generating the data for the substrate 302, the substrate measurement subsystem 340 may transmit the generated data to the system controller 328. In response to receiving the data from the substrate measurement subsystem 340, the system controller 328 may store the data in a data store 350.

[0053] 4 is a schematic cross-sectional side view of a substrate measurement subsystem 400 according to an aspect of the present disclosure. The substrate measurement subsystem 400 may be configured to obtain measurements for one or more portions of a substrate, such as the substrate 302 of FIG. 3 , before or after processing the substrate 302 in a processing chamber. The substrate measurement subsystem 400 may obtain spectral measurements for the portions of the substrate 302 by generating data (e.g., spectral data, non-spectral data, etc.) associated with the portions of the substrate 302. In some embodiments, the substrate measurement subsystem 400 may be configured to generate spectral data, non-spectral data, positional data, and / or other characteristic data associated with the substrate 302. The substrate measurement subsystem 400 may include a controller 430 configured to execute one or more instructions to generate data associated with the portions of the substrate 302.

[0054] The substrate measurement subsystem 400 may detect that the substrate 302 has been transferred to the substrate measurement subsystem 400. In response to detecting that the substrate 302 has been transferred to the substrate measurement subsystem 400, the substrate measurement subsystem 400 may determine the position and / or orientation of the substrate 302. The position and / or orientation of the substrate 302 may be determined based on an identification of a reference position of the substrate 302. The reference position may be a portion of the substrate 302 that includes an identification feature associated with the particular portion of the substrate 302. The controller 328 may determine the identification feature associated with the particular portion of the substrate 302 based on the determined identification information for the substrate 302.

[0055] The controller 430 can identify a reference position for the substrate 302 using one or more camera components 450 configured to capture image data for the substrate 302. The camera components 450 can generate image data for one or more portions of the substrate 302 and transmit the image data to the controller 430. The controller 430 can analyze the image data to identify an identifying feature associated with the reference position of the substrate 302. The controller 430 can further determine a position and / or orientation of the substrate 302 indicated in the image data based on the identified identifying feature of the substrate 302. The controller 430 can determine the position and / or orientation of the substrate 302 based on the identified identifying feature of the substrate 302 and the determined position and / or orientation of the substrate 302 indicated in the image data. In response to determining the position and / or orientation of the substrate 302, the controller 430 can generate position data associated with one or more portions of the substrate 302. In some embodiments, the position data may include one or more coordinates (e.g., Cartesian coordinates, polar coordinates, etc.) each associated with a portion of the substrate 302, each coordinate determined based on a distance from a reference position of the substrate 302.

[0056] The substrate measurement subsystem 400 may include one or more measurement components for measuring the substrate 302. In some embodiments, the substrate measurement subsystem 400 may include one or more spectral sensing components 420 configured to generate spectral data for one or more portions of the substrate 302. As previously described, the spectral data may correspond to the intensity of the detected wave of energy (i.e., the intensity or amount of energy) per wavelength of the detected wave. Further details regarding the collected spectral data are provided with respect to FIG. 5.

[0057] The spectral sensing component 420 may be configured to detect energy waves reflected from the portion of the substrate 302 and generate spectral data associated with the detected waves. The spectral sensing component 420 may include a wave generator 422 and a reflected wave receiver 424. In some embodiments, the wave generator 422 may be a light wave generator configured to generate a beam of light toward the portion of the substrate 302. In such embodiments, the reflected wave receiver 424 may be configured to receive a reflected light beam from the portion of the substrate 302. The wave generator 422 may be configured to generate an energy flow 426 (e.g., a light beam) and transmit the energy flow 426 to the portion of the substrate 302. A reflected energy wave 428 may be reflected from the portion of the substrate 302 and received by the reflected wave receiver 424. Although FIG. 3A shows a single energy wave reflected from the surface of the substrate 302, multiple energy waves may be reflected from the surface of the substrate 302 and received by the reflected wave receiver 424.

[0058] In response to the reflected wave receiver 424 receiving the reflected energy waves 428 from the portion of the substrate 302, the spectral sensing component 420 can measure the wavelength of each wave included in the reflected energy waves 428. The spectral sensing component 420 can further measure the intensity of each measured wavelength. In response to measuring each wavelength and each wavelength intensity, the spectral sensing component 420 can generate spectral data for the portion of the substrate 302. The spectral sensing component 420 can transmit the generated spectral data to a controller 430. In response to receiving the generated spectral data, the controller 430 can generate a mapping between the received spectral data and position data for the measured portion of the substrate 302.

[0059] The substrate measurement subsystem 400 may be configured to generate a particular type of spectral data based on the type of measurements acquired by the substrate measurement subsystem 400. In some embodiments, the spectral sensing component 420 may be a first spectral sensing component configured to generate one type of spectral data. For example, the spectral sensing component 420 may be configured to generate reflectometry spectral data, ellipsometry spectral data, hyperspectral imaging data, chemical imaging data, thermal spectral data, or conductivity spectral data. In such embodiments, the first spectral sensing component may be removed from the substrate measurement subsystem 400 and replaced with a second spectral sensing component configured to generate a different type of spectral data (e.g., reflectometry spectral data, ellipsometry spectral data, hyperspectral imaging data, chemical imaging data, eddy current spectral data, thermal spectral data, or conductivity spectral data).

[0060] In some embodiments, one or more measurement components, such as the spectral sensing component 420, may be stationary components within the substrate measurement subsystem 400. In such embodiments, the substrate measurement subsystem 400 may include one or more positioning components 440 configured to modify the position and / or orientation of the substrate 302 relative to the spectral sensing component 420. In some embodiments, the positioning components 440 may be configured to translate the substrate 302 relative to the spectral sensing component 420 along a first axis and / or a second axis. In other or similar embodiments, the positioning components 440 may be configured to rotate the substrate 302 relative to the spectral sensing component 420 about a third axis.

[0061] Once the spectral sensing component 420 generates spectral data for one or more portions of the substrate 302, the position component 440 can modify the position and / or orientation of the substrate 302 according to the one or more determined portions measured for the substrate 302. For example, before the spectral sensing component 420 generates spectral data for the substrate 302, the position component 440 can position the substrate 302 at Cartesian coordinate (0,0), and the spectral sensing component 420 can generate first spectral data for the substrate 302 at Cartesian coordinate (0,0). In response to the spectral sensing component 420 generating the first spectral data for the substrate 302 at Cartesian coordinate (0,0), the position component 440 can translate the substrate 302 along a first axis, such that the spectral sensing component 420 is configured to generate second spectral data for the substrate 302 at Cartesian coordinate (0,1). In response to the spectral sensing component 420 generating the second spectral data for the substrate 302 at Cartesian coordinate (0,1), the controller 430 can rotate the substrate 302 along a second axis, such that the spectral sensing component 420 is configured to generate third spectral data for the substrate 302 at Cartesian coordinate (1,1). This process can be performed multiple times until spectral data is generated for each determined portion of the substrate 302.

[0062] In some embodiments, one or more layers 412 of material may be included on the surface of the substrate 302. The one or more layers 412 may include an etching material, a photoresist material, a mask material, a deposition material, etc. In some embodiments, the one or more layers 412 may include an etching material that is to be etched according to an etching process performed in a processing chamber. In such embodiments, spectral data may be collected for one or more portions of the unetched etching material of the layer 412 deposited on the substrate 302 according to previously disclosed embodiments. In other or similar embodiments, the one or more layers 412 may include an etching material that has already been etched according to an etching process in a processing chamber. In such embodiments, one or more structural features (e.g., lines, columns, openings, etc.) may be etched into the one or more layers 412 of the substrate 302. In such embodiments, spectral data may be collected for one or more structural features etched into the one or more layers 412 of the substrate 302.

[0063] In response to receiving at least one of the spectral data, positional data, or property data for the substrate 302, the controller 430 may transmit the received data to the system controller 328 for processing and analysis according to embodiments described herein.

[0064] FIG. 5 illustrates spectral data 500 collected for a substrate according to an embodiment of the present disclosure. The spectral data can be generated from reflected energy received by a sensor in a processing chamber, such as the substrate measurement subsystem 400 of FIG. 4 or the processing chambers 314, 316, and 318 of FIG. 3 according to an embodiment of the present disclosure. As shown, the reflected energy waves received by the substrate measurement subsystem 400 can include multiple wavelengths. Each reflected energy wave can be associated with a different portion of the substrate 302. In some embodiments, an intensity can be measured for each reflected energy wave received by the substrate measurement subsystem 400. As seen in FIG. 5, an intensity can be measured for each wavelength of the reflected energy waves received by the substrate measurement subsystem 400. The association of each intensity with each wavelength can form the basis for forming the spectral data 500. In some embodiments, one or more wavelengths can be associated with intensity values ​​that are outside of an expected range of intensity values. For example, line 510 can be associated with intensity values ​​that are outside of the expected range of intensity values ​​shown by line 520. In such an embodiment, an intensity value that is outside the expected range of intensity values ​​can be an indication of the presence of a defect in a portion of the substrate 302. According to the above-described embodiments, modifications can be made to the process recipe for the substrate 302 based on the indication of defects in the portion of the substrate 302 .

[0065] 6 is a flowchart of a method 600 for estimating metrology values ​​for a profile of a substrate using a machine learning model, according to an aspect of the present disclosure. Method 600 is performed by processing logic, which may include hardware (circuitry, dedicated logic, etc.), software (such as running on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In some embodiments, method 600 may be performed using prediction server 112 and trained machine learning model 190 of FIG. 1. In other or similar embodiments, one or more blocks of FIG. 6 may be performed by one or more other machines not shown in FIG. 1.

[0066] At block 610, processing logic receives spectral data for a substrate being processed in the manufacturing system. In some embodiments, the spectral data may be received from a substrate measurement subsystem or another part of the manufacturing system, according to previously described embodiments.

[0067] At block 620, processing logic provides spectral data for the substrate as input to the trained machine learning model. At block 630, processing logic obtains output from the machine learning model. At block 640, processing logic extracts confidence data from the output obtained at block 630. In some embodiments, the confidence data includes a confidence that the profile of the substrate is associated with the measurement. In one example, the confidence is a real number between 0 and 1. Note that the confidence need not be a probability. For example, the sum of the confidences for all measurements need not be 1.

[0068] At block 650, processing logic uses the confidence data to estimate a metrology value for a substrate being processed in the manufacturing system. In some embodiments, if the confidence for the metrology value meets a threshold condition, the substrate is identified as being associated with the metrology value. At block 660, processing logic may provide a display of the estimated metrology value to a user of the manufacturing system.

[0069] In some embodiments, one or more sensors included in one part of the manufacturing system may be the same or similar type as sensors included in another part of the manufacturing system. For example, one or more sensors included in a substrate measurement subsystem configured to generate spectral data for substrates may be the same or similar type as sensors included in a process chamber also configured to generate spectral data for substrates. In such embodiments, a machine learning model can be trained using spectral data generated for sensors in the substrate measurement subsystem or process chamber, in accordance with previously described embodiments. Spectral data collected from the substrate measurement subsystem or process chamber can be used as training input for the trained machine learning model. Output from the trained machine learning model can be used to extract metrology measurements associated with the substrate, in accordance with previously described embodiments. Thus, in some embodiments, a machine learning model trained using spectral data collected from the substrate measurement subsystem can be used to determine metrology measurements using input spectral data obtained from the process chamber.

[0070] 7A-7C illustrate an example GUI 700 that provides a display of metrology measurements for a portion of a substrate, in accordance with aspects of the present disclosure. In some embodiments, the GUI 700 may be displayed to a user of a manufacturing system via a client device of the manufacturing system.

[0071] The GUI 700 may include a first portion 710 that displays one or more interactive components. The first portion 710 may include a chamber selection component that allows a user to select an identifier for a processing chamber of a manufacturing system. In response to selecting the identifier for the processing chamber, data about the substrate processed in the selected chamber may be displayed via other portions of the GUI 700. In some embodiments, the chamber selection component may include a drop-down menu that provides a list of one or more processing chambers of the manufacturing system that are available for user selection. In other or similar embodiments, the chamber selection component may include any other type of component that may facilitate user selection of an identifier for a processing chamber.

[0072] The first portion 710 may further include a recipe selection component that allows a user to select an identifier for an operation of a substrate process recipe. In response to selecting an identifier for the operation, data associated with the selected operation of the process recipe may be displayed via other portions of the GUI 700. In some embodiments, the recipe selection component may include a drop-down menu that provides a list of one or more process recipe operations available for user selection. In other or similar embodiments, the recipe selection component may include any other type of component that may facilitate user selection of an identifier for an operation.

[0073] The first portion 710 may further include a time period selection component that allows a user to select a time period for a process performed on the manufacturing system. In response to a time period selection, data associated with substrates processed on the manufacturing system within the selected time period may be displayed via other portions of the GUI 700. In some embodiments, the time period selection component may include a calendar component that provides a calendar showing specific dates and / or times when substrate processes were performed on the manufacturing system. A user of the manufacturing system may select a first date and / or time and a second date and / or time via the time period selection component of the first portion 710 of the GUI 700. The selected first date and / or time and the selected second date and / or time may define a selected time period. In other or similar embodiments, the time period selection component may include any other type of component that may facilitate user selection of a time period.

[0074] First portion 710 may further include one or more additional components that enable a user to select or provide additional settings associated with a process being executed in the manufacturing system. For example, first portion 710 may include a lower control limit component and / or an upper control limit component that enable a user to provide a lower control limit and / or an upper control limit associated with the process. In another example, first portion 710 may include a threshold component that enables a user to provide a threshold value associated with the process. Any other type of component that may facilitate a user to select or provide additional settings associated with a process may be included in first portion 710.

[0075] The GUI 700 may further include a second portion 712 that provides metrology data associated with substrates processed in the manufacturing system. In some embodiments, the metrology data may be associated with two or more substrates processed in the manufacturing system. In such embodiments, the metrology data may be displayed in a graphical format, such as the graph shown with respect to FIG. 7. In other or similar embodiments, the metrology data may be displayed in any other format suitable for displaying metrology data.

[0076] The GUI 700 may further include a second portion 714 that provides a contour map associated with a substrate processed in the manufacturing system. The contour map may provide a user with a visual representation of one or more metrology measurements for a portion of the substrate. For example, the contour map may provide a user with a visual representation of a film thickness or etch rate associated with the substrate.

[0077] In some embodiments, various types of substrates may be processed in a manufacturing system. For example, blanket wafers or patterned wafers may be processed in the manufacturing system. The GUI 700 may provide one or more windows for displaying data associated with each different type of substrate processed in the manufacturing system. A third portion of the GUI 700 may include a window selector 716 that facilitates transitioning between different windows displayed via the GUI 700. A user may select an option via the window selector 716 to cause different windows associated with types of substrates to be displayed via the GUI 700. For example, as shown in FIG. 7A , data associated with blanket wafers may be displayed via the GUI 700 in response to a user selecting the “Blanket” option in the window selector 716. Data associated with patterned wafers may be displayed via the GUI 700 in response to a user selecting the “Patterned” option in the window selector 716.

[0078] In some embodiments, different types of metrology data may be displayed to a user via GUI 700 depending on the selected option of window selector 716. As shown in FIG. 7B , in response to a user selecting the “Patterned” option of window selector 716, data associated with one or more patterned wafers processed in a manufacturing system is provided. In some embodiments, in response to a user selecting the “Patterned” option of window selector 716, data associated with one or more substrate critical dimensions (referred to as CD index) may be displayed via second portion 712 of GUI 700. In other or similar embodiments, data associated with another metrology measurement (e.g., etch rate, etch rate uniformity, critical dimension uniformity, edge-to-edge placement error, etc.) may be displayed via second portion 812.

[0079] In some embodiments, a user can view the data used to generate one or more components of GUI 700 (e.g., the graphs provided in second portion 712) by selecting the “Raw Data” option in window selector 716. As shown in FIG. 7C , in response to a user selecting the “Raw Data” option in window selector 716, raw data 720 associated with one or more substrates processed in the manufacturing system can be provided. The raw data 720 can include a timestamp of when measurements were generated for the substrate, an identifier for the lot that includes the substrate, an identifier for the substrate, an operation of the process recipe for the substrate, an identifier for a loop (i.e., two or more repeating operations) of the process recipe, position data associated with the substrate, and a model thickness for the substrate.

[0080] In some embodiments, the first portion 710 of the GUI 700 may be displayed regardless of the windows provided through the GUI 700. In other or similar embodiments, the first portion 710 may not be displayed for the various windows provided by the GUI 700.

[0081] FIG. 8 is a flowchart of a method 800 for generating training data for training a machine learning model according to an aspect of the present disclosure. FIG. 10 is a flowchart of a method 1000 for determining metrology measurements for a substrate in a manufacturing system according to an aspect of the present disclosure. FIG. 11 is a flowchart of another method 1100 for determining metrology measurements for a substrate in a manufacturing system according to an aspect of the present disclosure. Methods 800, 1000, and / or 1100 may be performed by processing logic, which may include hardware (circuitry, dedicated logic, etc.), software (such as running on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In some embodiments, methods 800, 1000, and / or 1100 may be performed by training set generator 172 of FIG. 1. In other or similar embodiments, one or more blocks of FIG. 8, FIG. 10, or FIG. 11 may be performed by one or more other machines not shown in FIG. 1.

[0082] As previously discussed, FIG. 8 is a flowchart of a method 800 for generating training data for training a machine learning model. At block 810, processing logic acquires spectral data associated with a first portion of a first previous substrate in the manufacturing system and at least one of a second portion of the first previous substrate or a third portion of a second previous substrate in the manufacturing system. The first previous substrate and / or the second previous substrate may correspond to the substrate 302 described herein. In some embodiments, the spectral data may be collected by the substrate measurement subsystem 400, as previously discussed. In additional or alternative embodiments, the spectral data may be collected according to other techniques.

[0083] At block 820, processing logic identifies metrology measurements obtained for at least one of the second portion of the first previous substrate or the third portion of the second previous substrate. In some embodiments, metrology measurements may be obtained using metrology instrument 128 for the second portion of the first previous substrate and / or the third portion of the second previous substrate, but not for the first portion of the first previous substrate. FIG. 9 shows an exemplary substrate 910 and one or more portions of substrate 910 in accordance with aspects of the present disclosure. In exemplary examples, metrology measurements may be generated (e.g., by metrology instrument 128) for portions 912A, 914A and / or other portions of substrate 910 (e.g., one or more of portion 916, portion 918, etc.). Processing logic may determine metrology measurements for other portions of substrate 910, such as portions 912B, 914B, 920, and / or portions of another substrate, according to embodiments and examples presented below.

[0084] Returning to FIG. 8 , at block 830, processing logic determines metrology measurements associated with the first portion of the first previous substrate based on the identified one or more metrology measurements. The metrology measurements for the portion of the substrate located at a particular radial distance from the center point of the substrate may correspond to (e.g., may be the same or similar to) metrology measurements for other portions of the substrate associated with particular radial distances from the center point. The radial distance refers to the distance between the center point of a circular (or approximately circular) shaped object and another point (e.g., not the center point) of the circular (or approximately circular) shaped object. In some embodiments, processing logic may determine the metrology measurements associated with the first portion of the first previous substrate based on metrology measurements generated at portions located at the same or similar radial distances from the center of the first previous substrate.

[0085] In an illustrative example, portion 916 of substrate 910 may be at or near the center point of substrate 910. Portion 912A of substrate 910 may be located at a first radial distance 922A from portion 916. In some embodiments, as described above, spectral data may be generated on portion 912B of substrate 910. Metrology measurements may not be generated for portion 912B. Processing logic may determine that portion 912B of substrate 910 is also located at or near the first radial distance 922A from portion 916. Thus, processing logic may determine that metrology measurements for portion 912B correspond to (e.g., are the same or substantially the same as) metrology measurements generated for portion 912A. In another illustrative example, portion 914A of substrate 910 may be located at a second radial distance 922B from portion 916. Processing logic may determine that portion 914B is also located at or near the second radial distance 922B from portion 916. Thus, processing logic can determine that the metrology measurements for portion 914B correspond to the metrology measurements for portion 914A.

[0086] In additional or alternative embodiments, according to the embodiment of FIG. 10 , processing logic may determine metrology measurements associated with a first portion of a first prior substrate based on one or more outputs of the function. As previously discussed, FIG. 10 is a flowchart of a method 1000 for determining metrology measurements for a substrate in a manufacturing system according to aspects of the present disclosure. At block 1010, processing logic determines a first coordinate associated with the first portion of the first substrate and a second coordinate associated with a second portion of the first substrate and / or a third portion of the second substrate. In some embodiments, processing logic may determine the first coordinate and / or the second coordinate based on position data collected by the substrate measurement subsystem 400, as previously discussed. The coordinates may include Cartesian coordinates, polar coordinates, etc.

[0087] At block 1020, processing logic may provide an indication of the first coordinate, the second coordinate, and the metrology measurement obtained for at least one of the second portion of the first prior substrate or the third portion of the second prior substrate as inputs to a function. The function may include a linear interpolation function, an extrapolation function, a nearest neighbor interpolation function, a Euclidean distance function, etc. At block 1030, processing logic may obtain one or more outputs of the function. The one or more outputs may include an indication of the metrology measurement associated with the first portion of the first prior substrate. At block 1040, processing logic determines the metrology measurement associated with the first portion of the first prior substrate based on the obtained one or more outputs.

[0088] In an illustrative example, metrology instrument 128 may, in some embodiments, generate metrology data for one or more of portions 916 and / or portions 918 of substrate 910. Substrate measurement subsystem 400 may generate spectral data for portion 916, one or more of portions 918, and / or portion 920, as described above. Processing logic may provide coordinates associated with portions 916, 918, and / or 920, along with metrology measurements generated for portion 916 and / or one or more portions 918, as inputs to a linear interpolation function. In some embodiments, the linear interpolation function may interpolate metrology measurements for portion 920 based on the provided coordinates associated with portions 916, 918, and / or 920 and the metrology measurements generated for portion 916 and / or one or more portions 918. Thus, processing logic may determine metrology measurements associated with portion 920 based on one or more outputs of the linear interpolation function.

[0089] 11 , processing logic may determine metrology measurements associated with the first portion of the first prior substrate based on one or more outputs of the machine learning model. As previously discussed, FIG. 11 is a flowchart of another method 1100 of determining metrology measurements for a substrate in a manufacturing system according to aspects of the present disclosure. At block 1110, processing logic may obtain context data associated with the first prior substrate. The context data may include one or more of: a first coordinate associated with the first portion of the first prior substrate; a substrate process that has previously been performed and / or will be performed on the first prior substrate; a duration for which the substrate process has been performed or will be performed; a duration for which spectral data for the first portion of the first prior substrate was collected; an indication of one or more types of equipment associated with the substrate process; and the like.

[0090] At block 1120, processing logic may provide the spectral data associated with the first portion of the first prior substrate and the acquired contextual data as inputs to a machine learning model. In some embodiments, the machine learning model may be trained to predict metrology measurements for prior substrates based on given spectral data and contextual data for prior substrates in the manufacturing system. In some embodiments, the machine learning model may be trained using a dataset including training inputs indicative of spectral data and / or contextual data associated with prior substrates in the manufacturing system. The dataset may additionally or alternatively include target outputs for the training inputs, where the target outputs are indicative of one or more metrology measurements collected for the prior substrate. The machine learning model 190 may use one or more of a support vector machine (SVM), a radial basis function (RBF), clustering, supervised machine learning, semi-supervised machine learning, unsupervised machine learning, a k-nearest neighbor algorithm (k-NN), linear regression, random forests, a neural network (e.g., an artificial neural network), or the like.

[0091] In an example embodiment, the training inputs of the dataset can include spectral data and / or contextual data associated with the second portion of the first prior substrate and / or the third portion of the second prior substrate, and the target outputs for the training inputs can include metrology measurements generated for the second portion of the first prior substrate and / or the third portion of the second prior substrate.

[0092] At block 1130, processing logic may obtain one or more outputs of the machine learning model. The one or more outputs may include metrology data indicative of one or more sets of metrology measurements and, for each set of metrology measurements, a confidence level that the respective set of metrology measurements corresponds to the first portion of the first prior substrate. At block 1140, processing logic extracts metrology measurements associated with the first portion of the first prior substrate from the one or more outputs. The processing logic may extract the metrology measurements from the one or more outputs by identifying each set of metrology measurements having a confidence level that meets a confidence criterion (e.g., exceeds a confidence threshold value). The identified set of metrology measurements may include metrology measurements for the first portion of the first prior substrate.

[0093] Returning to FIG. 8 , at block 840, processing logic may generate training data for training a machine learning model to predict metrology measurements for a current substrate in a manufacturing system by performing the operations of block 842 and / or block 844. At block 842, processing logic may generate a first training input including spectral data associated with a first portion of a first prior substrate. At block 844, processing logic may generate a first target output for the first training input. The first target output includes determined metrology measurements (e.g., determined according to the above embodiments) associated with the first portion of the first prior substrate. In additional or alternative embodiments, processing logic may generate a second training input including spectral data associated with at least one of a second portion of the first prior substrate and / or a third portion of the second prior substrate. Processing logic may generate a second target output for the second training input, the second target output including metrology measurements generated for at least one of the second portion of the first prior substrate and / or the third portion of the second prior substrate. At block 850, processing logic provides training data for training the machine learning model with respect to (i) a set of training inputs including the first training input (and / or the second training input) and (ii) a set of target outputs including the first target output (and / or the second target output).

[0094] As previously described, once trained, the machine learning model may be configured to predict metrology measurements associated with a current substrate in a manufacturing system based on given spectral data. In some embodiments, the machine learning model described with respect to Figure 8 may differ from the machine learning model described with respect to Figure 11 because the machine learning model in Figure 11 was trained to predict metrology measurements based on spectral data and contextual data associated with a previous substrate in a manufacturing system, whereas the machine learning model described with respect to Figure 8 was trained to predict metrology measurements based on spectral data (e.g., not contextual data) associated with a current substrate in a manufacturing system.

[0095] In some embodiments, a machine learning model may be trained to predict metrology measurements for a current substrate in a manufacturing system according to the embodiments of both Figures 2 and 8. In some embodiments, the weights of the trained machine learning model may be adjusted (e.g., by a developer, engineer, operator, etc. of the manufacturing system) based on the source of the metrology measurements used to train the machine learning model. For example, some metrology measurements may be generated by metrology equipment 128 as described with respect to Figures 2 and 8, while other metrology measurements are determined according to the embodiments described with respect to Figures 9-11. In some embodiments, the weights of the trained machine learning model may be adjusted such that the weights associated with the generated metrology measurements are greater than the weights associated with the determined metrology measurements.

[0096] FIG. 12 is a block diagram of an exemplary computer system 1200 operating in accordance with one or more aspects of the present disclosure. In alternative embodiments, the machine may be connected (e.g., networked) to other machines in a local area network (LAN), an intranet, an extranet, or the Internet. The machine may operate in the capacity of a server or client machine in a client-server network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine may be a personal computer (PC), a tablet computer, a set-top box (STB), a personal digital assistant (PDA), a mobile phone, a web appliance, a server, a network router, a switch, or a bridge, or any machine capable of executing a set of instructions (sequential or non-sequential) that specify operations to be performed by the machine. Furthermore, while only a single machine is shown, the term “machine” should also be understood to include any collection of machines (e.g., computers) that individually or jointly execute a set (or sets) of instructions to perform any one or more of the methods described herein. In an embodiment, computing device 1200 may correspond to system controller 328 of FIG. 3 or controller 430 of FIG. 4.

[0097] The exemplary computing device 1200 includes a processing device 1202, a main memory 1204 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM) such as synchronous DRAM (SDRAM), etc.), a static memory 1206 (e.g., flash memory, static random access memory (SRAM), etc.), and a secondary memory (e.g., a data storage device 1228), which communicate with each other via a bus 1208.

[0098] The processing device 1202 may represent one or more general-purpose processors, such as a microprocessor, a central processing unit, or the like. More specifically, the processing device 1202 may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor implementing other instruction sets, or a processor implementing a combination of instruction sets. The processing device 1202 may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), a network processor, or the like. The processing device 1202 may also be or include a system on a chip (SoC), a programmable logic controller (PLC), or other type of processing device. The processing device 1202 is configured to execute processing logic for performing the operations and steps described herein.

[0099] Computing device 1200 may further include a network interface device 1222 for communicating with a network 1264. Computing device 1200 may also include a video display unit 1210 (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)), an alphanumeric input device 1212 (e.g., a keyboard), a cursor control device 1214 (e.g., a mouse), and a signal generation device 1220 (e.g., a speaker).

[0100] The data storage device 1228 may include a machine-readable storage medium (or, more specifically, a non-transitory computer-readable storage medium) 1224 on which is stored one or more sets of instructions 1226 that embody any one or more of the methods or functions described herein. Here, non-transitory storage medium refers to a storage medium other than a carrier wave. The instructions 1226 may also reside, completely or at least partially, within the main memory 1204 and / or within the processing device 1202 during execution by the computing device 1200, with the main memory 1204 and the processing device 1202 also constituting computer-readable storage media.

[0101] The computer-readable storage medium 1224 may also be used to store the model 190 and data used to train the model 190. The computer-readable storage medium 1224 may also store a software library containing methods for invoking the model 190. While the computer-readable storage medium 1224 is shown as a single medium in the exemplary embodiment, the term "computer-readable storage medium" should be understood to include a single medium or multiple media (e.g., centralized or distributed databases and / or associated caches and servers) that store one or more sets of instructions. The term "computer-readable storage medium" should also be understood to include any medium capable of storing or encoding a set of instructions that are executed by a machine and cause the machine to perform any one or more of the methods of the present disclosure. Thus, the term "computer-readable storage medium" should be understood to include, but is not limited to, solid-state memory, and optical and magnetic media.

[0102] The foregoing description sets forth numerous specific details, such as examples of particular systems, components, methods, etc., to provide a thorough understanding of some embodiments of the present disclosure. However, it will be apparent to those skilled in the art that at least some embodiments of the present disclosure can be practiced without these specific details. In other instances, well-known components or methods have not been described in detail or have been presented in simple block diagram form to avoid unnecessarily obscuring the present disclosure. Thus, the specific details described are for illustrative purposes only. A particular implementation may vary from these example details and still be considered to be within the scope of the present disclosure.

[0103] References throughout this specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment. Thus, the appearances of the phrase "in one embodiment" or "in an embodiment" in various places throughout this specification do not necessarily all refer to the same embodiment. In addition, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." When the term "about" or "approximately" is used herein, it is intended to mean that the stated nominal value is accurate to within ±10%.

[0104] Although the operations of the methods herein are illustrated and described in a particular order, the order of the operations of each method may be changed so that certain operations are performed in reverse order and certain operations are performed at least partially concurrently with other operations. In alternative embodiments, instructions or sub-operations of separate operations may be intermittent and / or interleaved.

[0105] It is to be understood that the above description is intended to be illustrative, and not limiting. Many other embodiments will be apparent to those skilled in the art upon reading and understanding the above description. The scope of the present disclosure should, therefore, be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

Claims

1. acquiring spectral data associated with a first portion of a first previous substrate in a manufacturing system and at least one of a second portion of the first previous substrate or a third portion of a second previous substrate in the manufacturing system; identifying one or more metrology measurements taken on the at least one of the second portion of the first previous substrate or the third portion of the second previous substrate; determining a metrology measurement associated with the first portion of the first previous substrate based on the identified one or more metrology measurements; generating training data for training a machine learning model to predict metrology measurements of current substrates in the manufacturing system, wherein generating the training data includes: generating a first training input including the spectral data associated with the first portion of the first prior substrate; and generating a first target output for the first training input, the first target output including the determined metrology measurement associated with the first portion of the first previous substrate; generating training data, providing the training data to train the machine learning model with respect to (i) a set of training inputs comprising the first training input, and (ii) a set of target outputs comprising the first target output; A method comprising:

2. determining the metrology measurements associated with the first portion of the first previous substrate; providing as inputs to a function an indication of one or more first coordinates associated with the first portion of the first previous substrate, one or more second coordinates associated with at least one of the second portion of the first previous substrate or the third portion of the second previous substrate, and the one or more metrology measurements measured on the at least one of the second portion of the first previous substrate or the third portion of the second previous substrate; The method of claim 1 , wherein the metrology measurement associated with the first portion of the substrate is determined based on one or more outputs of the function.

3. The method of claim 2 , wherein the function comprises at least one of a linear interpolation function, an extrapolation function, a nearest neighbor interpolation function, or a Euclidean distance function.

4. determining the metrology measurements associated with the first portion of the substrate; providing the acquired spectral data associated with the first portion of the first prior substrate and contextual data associated with the first prior substrate as input to an additional machine learning model, wherein the additional machine learning model is trained to predict metrology measurements of the prior substrate based on given spectral data and contextual data for prior substrates in the manufacturing system, the additional machine learning model being trained using a dataset including the spectral data associated with the at least one of the second portion of the first prior substrate or the third portion of the second prior substrate and the one or more metrology measurements measured on at least one of the second portion of the first prior substrate or the third portion of the second prior substrate; extracting the metrology measurements from one or more outputs of the additional machine learning model; The method of claim 1 , comprising:

5. the one or more outputs of the additional machine learning model include metrology data indicative of one or more sets of metrology measurements and, for each set of metrology measurements, a confidence level that the respective set of metrology measurements corresponds to the first portion of the first prior substrate; extracting the metrology measurements from the one or more outputs; 5. The method of claim 4, comprising identifying a respective set of metrology measurements having a confidence level that meets a confidence criterion, the identified respective set of metrology measurements including the metrology measurement.

6. 5. The method of claim 4, wherein the context data associated with the first prior substrate includes at least one of one or more first coordinates associated with the first portion of the first prior substrate, a substrate process performed on the first prior substrate, a period during which the substrate process was performed on the first prior substrate, a period during which the spectral data for the first portion of the first prior substrate was collected, or an indication of one or more types of equipment used to perform the substrate process.

7. determining the metrology measurements associated with the first portion of the first previous substrate; determining a first radial distance between a central portion of the first previous substrate and the first portion of the first previous substrate; determining a second radial distance between at least one of the central portion of the first previous substrate and the second portion of the first previous substrate or the central portion of the second previous substrate and the third portion of the second previous substrate; responsive to determining that the first radial distance corresponds to the second radial distance, determining that the metrology measurement associated with the first portion of the first previous substrate corresponds to at least one of the identified one or more metrology measurements obtained on the at least one of the second portion of the first previous substrate or the third portion of the second previous substrate; The method of claim 1 , comprising:

8. generating the training data, generating a second training input including the spectral data associated with the at least one of the second portion of the first prior substrate or the third portion of the second prior substrate; generating a second target output for the second training input, the second target output including the one or more metrology measurements measured on the at least one of the second portion of the first previous substrate or the third portion of the second previous substrate; further comprising The method of claim 1 , wherein the set of training inputs further comprises the second training input and the set of target outputs further comprises the second target output.

9. Memory and a processing device coupled to the memory; and wherein the processing device: acquiring spectral data associated with a first portion of a first previous substrate in a manufacturing system and at least one of a second portion of the first previous substrate or a third portion of a second previous substrate in the manufacturing system; identifying one or more metrology measurements taken on the at least one of the second portion of the first previous substrate or the third portion of the second previous substrate; determining a metrology measurement associated with the first portion of the first previous substrate based on the identified one or more metrology measurements; generating training data for training a machine learning model to predict metrology measurements of current substrates in the manufacturing system, wherein generating the training data includes: generating a first training input including the spectral data associated with the first portion of the first prior substrate; and generating a first target output for the first training input, the first target output including the determined metrology measurement associated with the first portion of the first previous substrate; generating training data, providing the training data to train the machine learning model with respect to (i) a set of training inputs comprising the first training input, and (ii) a set of target outputs comprising the first target output; 2. A system for performing operations including:

10. determining the metrology measurements associated with the first portion of the first previous substrate; providing as inputs to a function an indication of one or more first coordinates associated with the first portion of the first previous substrate, one or more second coordinates associated with at least one of the second portion of the first previous substrate or the third portion of the second previous substrate, and the one or more metrology measurements measured on the at least one of the second portion of the first previous substrate or the third portion of the second previous substrate; The system of claim 9 , wherein the metrology measurement associated with the first portion of the substrate is determined based on one or more outputs of the function.

11. The system of claim 10 , wherein the function comprises at least one of a linear interpolation function, an extrapolation function, a nearest neighbor interpolation function, or a Euclidean distance function.

12. determining the metrology measurements associated with the first portion of the substrate; providing the acquired spectral data associated with the first portion of the first prior substrate and contextual data associated with the first prior substrate as input to an additional machine learning model, wherein the additional machine learning model is trained to predict metrology measurements of the prior substrate based on given spectral data and contextual data for prior substrates in the manufacturing system, the additional machine learning model being trained using a dataset including the spectral data associated with the at least one of the second portion of the first prior substrate or the third portion of the second prior substrate and the one or more metrology measurements measured on at least one of the second portion of the first prior substrate or the third portion of the second prior substrate; extracting the metrology measurements from one or more outputs of the additional machine learning model; The system of claim 9 , comprising:

13. the one or more outputs of the additional machine learning model include metrology data indicative of one or more sets of metrology measurements and, for each set of metrology measurements, a confidence level that the respective set of metrology measurements corresponds to the first portion of the first prior substrate; extracting the metrology measurements from the one or more outputs; 13. The system of claim 12, further comprising identifying a respective set of metrology measurements having a confidence level that meets a confidence criterion, the identified respective set of metrology measurements including the metrology measurement.

14. 13. The system of claim 12, wherein the context data associated with the first prior substrate includes at least one of one or more first coordinates associated with the first portion of the first prior substrate, a substrate process performed on the first prior substrate, a period during which the substrate process was performed on the first prior substrate, a period during which the spectral data for the first portion of the first prior substrate was collected, or an indication of one or more types of equipment used to perform the substrate process.

15. determining the metrology measurements associated with the first portion of the first previous substrate; determining a first radial distance between a central portion of the first previous substrate and the first portion of the first previous substrate; determining a second radial distance between at least one of the central portion of the first previous substrate and the second portion of the first previous substrate or the central portion of the second previous substrate and the third portion of the second previous substrate; responsive to determining that the first radial distance corresponds to the second radial distance, determining that the metrology measurement associated with the first portion of the first previous substrate corresponds to at least one of the identified one or more metrology measurements obtained on the at least one of the second portion of the first previous substrate or the third portion of the second previous substrate; The system of claim 9 , comprising:

16. 1. A non-transitory computer-readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to perform operations, the operations including: acquiring spectral data associated with a first portion of a first previous substrate in a manufacturing system and at least one of a second portion of the first previous substrate or a third portion of a second previous substrate in the manufacturing system; identifying one or more metrology measurements taken on the at least one of the second portion of the first previous substrate or the third portion of the second previous substrate; determining a metrology measurement associated with the first portion of the first previous substrate based on the identified one or more metrology measurements; generating training data for training a machine learning model to predict metrology measurements of current substrates in the manufacturing system, wherein generating the training data includes: generating a first training input including the spectral data associated with the first portion of the first prior substrate; and generating a first target output for the first training input, the first target output including the determined metrology measurement associated with the first portion of the first previous substrate; generating training data, providing the training data to train the machine learning model with respect to (i) a set of training inputs comprising the first training input, and (ii) a set of target outputs comprising the first target output; 1. A non-transitory computer-readable storage medium comprising:

17. determining the metrology measurements associated with the first portion of the first previous substrate; providing as inputs to a function an indication of one or more first coordinates associated with the first portion of the first previous substrate, one or more second coordinates associated with at least one of the second portion of the first previous substrate or the third portion of the second previous substrate, and the one or more metrology measurements measured on the at least one of the second portion of the first previous substrate or the third portion of the second previous substrate; 17. The non-transitory computer-readable storage medium of claim 16, wherein the metrology measurement associated with the first portion of the substrate is determined based on one or more outputs of the function.

18. 20. The non-transitory computer-readable storage medium of claim 17, wherein the function comprises at least one of a linear interpolation function, an extrapolation function, a nearest neighbor interpolation function, or a Euclidean distance function.

19. determining the metrology measurements associated with the first portion of the substrate; providing the acquired spectral data associated with the first portion of the first prior substrate and contextual data associated with the first prior substrate as input to an additional machine learning model, wherein the additional machine learning model is trained to predict metrology measurements of the prior substrate based on given spectral data and contextual data for prior substrates in the manufacturing system, the additional machine learning model being trained using a dataset including the spectral data associated with the at least one of the second portion of the first prior substrate or the third portion of the second prior substrate and the one or more metrology measurements measured on at least one of the second portion of the first prior substrate or the third portion of the second prior substrate; extracting the metrology measurements from one or more outputs of the additional machine learning model; 17. The non-transitory computer-readable storage medium of claim 16, comprising:

20. the one or more outputs of the additional machine learning model include metrology data indicative of one or more sets of metrology measurements and, for each set of metrology measurements, a confidence level that the respective set of metrology measurements corresponds to the first portion of the first prior substrate; extracting the metrology measurements from the one or more outputs; 20. The non-transitory computer-readable storage medium of claim 19, comprising identifying a respective set of metrology measurements having a confidence level that meets a confidence criterion, the identified respective set of metrology measurements including the metrology measurement.

Images