Process navigator for doe results checking in virtual fabrication platform

Abstract

Techniques for viewing virtual metrology data are provided. Virtual metrology data may be generated using trained models or simulation algorithms. A user interface may receive requests to view virtual metrology data. The virtual metrology data may be generated and / or retrieved in response to the request. An interactive user interface is displayed with the virtual metrology data. The interactive user interface facilitates viewing different virtual metrology data based on received selections.

Description

PROCESS NAVIGATOR FOR DOE RESULTS CHECKING IN VIRTUAL FABRICATION PLATFORMCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] A PCT Request Form is filed concurrently with this specification as part of the present application. Each application that the present application claims benefit of or priority to as identified in the concurrently filed PCT Request Form is incorporated by reference herein in their entireties and for all purposes.BACKGROUND

[0002] Many semiconductor fabrication processes are complicated to simulate or model. For process engineers designing recipes for fabrication processes, it can be difficult and timeconsuming to understand how process parameters may affect the fabrication process and the resulting substrate. For example, a fabrication process that requires multiple sequential steps may be difficult to simulate, because the result of one step is needed to perform simulation of the next step. It may be particularly difficult, or even impossible, to accurately simulate such a process.

[0003] The background description provided herein is for the purposes of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in this background section, as well as aspects of the description that may not otherwise qualify as prior art at the time of filing, are neither expressly nor impliedly admitted as prior art against the present disclosure.SUMMARY

[0004] Disclosed herein are methods and systems of generating and / or displaying virtual metrology data. In one aspect of the embodiments herein a method of displaying virtual metrology data is provided, the method including: receiving, via a user interface, a user- specified set of process parameters associated with a fabrication process and a range of process parameter values for each process parameter of the set of process parameters; and displaying, via the user interface, interactive elements that may receive a selection of a process parameter value of the range of process parameter values for each process parameter; receiving, via the user interface, a selection of a process parameter value for each process parameter; and updating the user interface to display virtual metrology data corresponding to the selection of process parameter values.

[0005] In some embodiments, the process parameters are input process parameters. In some embodiments, the process parameters are output process parameters. In some embodiments further including determining input process parameter values based on the output process parameter values, wherein the virtual metrology data is based on the input process parameter values. The method of claim 3, further including determining the input process parameter values by providing the output process parameter values to a trained model that represents a function that associates output process parameter values to input process parameter values such that a simulation of a fabrication process using the input process parameter values yields a simulated fabricated substrate having virtual metrology data that is substantially similar to the output process parameter values. In some embodiments, a virtual metrology data corresponding to an output process parameter value is within about 10% of the output process parameter value. In some embodiments further including: simulating the fabrication process using a first set of process parameter values by using a fabrication process simulation algorithm, wherein the first set of process parameter values corresponds to the selection of process parameter values, wherein the virtual metrology data is based on the simulation. In some embodiments, the range of process parameter values are used to perform a design of experiments (DoE) simulation of a fabrication process designed to simulate a solution space of the fabrication process. In some embodiments, the virtual metrology data includes an image of a 3-dimensional rendering of a simulated fabricated substrate generated by a simulated fabrication process, the simulated fabrication process performed based on the selection of process parameter values. In some embodiments further including: displaying, via the user interface, a user-manipulable view of the 3-dimensional rendering of the simulated fabricated substrate, and receiving, via the user interface, a selection of the view of the 3-dimensional rendering, wherein the image of the 3- dimensional rendering of the simulated fabricated substrate is based on the selection of the view. In some embodiments further including: receiving, via the user interface, an updated selection of a process parameter value for each process parameter; and updating the user interface to display updated virtual metrology data corresponding to the updated selection of process parameter values. In some embodiments, the set of process parameters includes at least 3 different process parameters. In some embodiments, the fabrication process includes an etching process or a deposition process.

[0006] In another aspect of the embodiments herein a non-transitory computer-readable medium including computer-readable instructions is provided that, when executed by one or more processors, cause the one or more processors to perform operations including: receiving, via a user interface, a user- specified set of process parameters associated with a fabricationprocess and a range of process parameter values for each process parameter of the set of process parameters; and displaying, via the user interface, interactive elements that may receive a selection of a process parameter value of the range of process parameter values for each process parameter; receiving, via the user interface, a selection of a process parameter value for each process parameter; and updating the user interface to display virtual metrology data corresponding to the selection of process parameter values.

[0007] In one aspect of the embodiments herein a method of displaying virtual metrology data is provided, the method , including: receiving, via a user interface, a user-specified set of input process parameters associated with a fabrication process and a baseline process parameter value for each process parameter of the set of input process parameters; generating virtual metrology data based on the baseline process parameter values and the set of input process parameters, wherein a first set of virtual metrology data is generated based on a first range of process parameter values for a first input process parameter of the set of input process parameters and the baseline process parameter values for input process parameters of the set of input process parameters that are not the first input process parameter; and displaying, via the user interface, the virtual metrology data.

[0008] In some embodiments, the virtual metrology data includes one or more charts of virtual metrology data as a function of the first input process parameter. In some embodiments further including receiving, via the user interface, the first range of process parameter values for the first input process parameter. In some embodiments further including generating the virtual metrology data by providing the baseline process parameter value for each process parameter and the first range of process parameter values to a trained model, wherein the model has been trained to predict virtual metrology data based on process parameter values. In some embodiments further including receiving, via the user interface, a selection of the trained model to generate the virtual metrology data from a plurality of trained models. In some embodiments, the trained model includes a trained neural network. In some embodiments, the trained model was trained using a design of experiments (DoE) simulation of the fabrication process designed to simulate a solution space of the fabrication process. In some embodiments, the fabrication process includes an etching process or a deposition process.

[0009] In another aspect of the embodiments herein a non-transitory computer-readable medium including computer-readable instructions is provided that, when executed by one or more processors, cause the one or more processors to perform operations including: receiving, via a user interface, a user-specified set of input process parameters associated with a fabrication process and a baseline process parameter value for each process parameter of theset of input process parameters; generating virtual metrology data based on the baseline process parameter values and the set of input process parameters, wherein a first set of virtual metrology data is generated based on a first range of process parameter values for a first input process parameter of the set of input process parameters and the baseline process parameter values for input process parameters of the set of input process parameters that are not the first input process parameter; and displaying, via the user interface, the virtual metrology data.

[0010] These and other features of the disclosed embodiments will be described in detail below with reference to the associated drawings.BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 presents a system for generating and / or viewing results of a process simulation or trained model according to various embodiments disclosed herein.

[0012] Figure 2 presents a flowchart for a process of providing an interactive user interface to view virtual metrology data according to various embodiments disclosed herein.

[0013] Figure 3 presents an example user interface to receive a request to view virtual metrology data according to various embodiments disclosed herein.

[0014] Figures 4A-B are example user interfaces for displaying virtual metrology data according to various embodiments disclosed herein.

[0015] Figure 5A-B are additional example user interfaces for displaying virtual metrology data according to various embodiments disclosed herein.

[0016] Figure 6 presents an example computer system that may be employed to implement certain embodiments described herein.DETAILED DESCRIPTIONTERMINOLOGY

[0017] The following terms are used throughout the instant specification:

[0018] The terms “semiconductor wafer,” “wafer,” “substrate,” “wafer substrate” and “partially fabricated integrated circuit” may be used interchangeably. Those of ordinary skill in the art understand that the term “partially fabricated integrated circuit” can refer to a semiconductor wafer during any of many stages of integrated circuit fabrication thereon. A wafer or substrate used in the semiconductor device industry typically has a diameter of 200 mm, or 300 mm, or 450 mm. This detailed description assumes the embodiments are implemented on a wafer. However, the disclosure is not so limited. The work piece may be of various shapes, sizes, and materials. Besides semiconductor wafers, other work pieces thatmay take advantage of the disclosed embodiments include various articles such as printed circuit boards, magnetic recording media, magnetic recording sensors, mirrors, optical elements, micro-mechanical devices and the like.

[0019] A “semiconductor device fabrication process” as used herein is an operation performed during fabrication of semiconductor devices. Typically, the overall fabrication process includes multiple semiconductor device fabrication processes, each performed in its own semiconductor fabrication tool such as a plasma reactor, an electroplating cell, a chemical mechanical planarization tool, a wet etch tool, and the like. Categories of semiconductor device fabrication processes include subtractive processes, such as etch processes and planarization processes, and material additive processes, such as deposition processes (e.g., physical vapor deposition, chemical vapor deposition, atomic layer deposition, electrochemical deposition, electroless deposition). In the context of etch processes, a substrate etch process includes processes that etch a mask layer or, more generally, processes that etch any layer of material previously deposited on and / or otherwise residing on a substrate surface. Such etch process may etch a stack of layers in the substrate.

[0020] “Manufacturing equipment” or “fabrication tool” refers to equipment in which a manufacturing process takes place that may produce defects in a semiconductor substrate or other workpiece. Manufacturing equipment often has a processing chamber in which the workpiece resides during processing. Typically, when in use, manufacturing equipment perform one or more semiconductor device fabrication processes. Examples of manufacturing equipment for semiconductor device fabrication include deposition reactors such as electroplating cells, physical vapor deposition reactors, chemical vapor deposition reactors, and atomic layer deposition reactors, and subtractive process reactors such as dry etch reactors (e.g., chemical and / or physical etch reactors), wet etch reactors, and ashers.

[0021] ‘ ‘Virtual Fabrication Environment” refers to software that may model and predict structures of semiconductor fabrication processes and devices in one, two, and / or three- dimensions. A virtual fabrication environment for a semiconductor device structure may offer a platform for performing semiconductor process development at a lower cost and higher speed than is possible with conventional trial-and-error physical experimentation. In contrast to conventional computer-aided design (CAD) and technology-CAD (TCAD) environments, a virtual fabrication environment is capable of virtually modeling an integrated process flow and predicting the complete 3D structures of all devices and circuits that comprise a full technology suite. Virtual fabrication can be described in its most simple form as combining a description of an integrated process sequence with a subject design, in the form of 2D design data (masksor layout), and producing a 3D structural model that is predictive of the result expected from a real / physical fabrication run. A 3D structural model includes the geometrically accurate 3D shapes of multiple layers of materials, implants, diffusions, etc. that comprise a chip or a portion of a chip.

[0022] Virtual fabrication may be done in a way that is primarily geometric, however the geometry involved is instructed by the physics of the fabrication processes. By performing the modeling at a structural level of abstraction (rather than physics-based simulations), construction of the structural models can be dramatically accelerated, enabling full technology modeling, at a circuit-level area scale. The use of a virtual fabrication environment thus provides fast verification of process assumptions, and visualization of the complex interrelationship between the integrated process sequence and the 2D design data. In some cases, a virtual fabrication environment may be configured to provide one or more virtual metrology measurement steps, which allow virtual metrology measurement data to be collected from modeled structures. The virtual metrology data may then be exported (e.g., to a data analysis tool, saved in a file or other document, etc.) and / or displayed to a user (e.g., such that the user can modify process steps based on the virtual metrology). In some embodiments, the techniques disclosed herein for performing a fabrication process simulation using process parameters may utilize virtual metrology techniques, e.g., to verify and / or validate that the simulated fabrication process meets user- specified targets.

[0023] In some embodiments, a virtual fabrication environment may utilize a 3D modeling engine which represents an underlying structural model in the form of voxels. Voxels are essentially 3D pixels. Each voxel is a cube of the same size, and may contain one or more materials, or no materials. Most of the operations performed by the 3D modeling engine may be voxel modeling operations. Modeling operations based on a digital voxel representation may be more robust than corresponding operations in a conventional analog solid modeling kernel. In some embodiments, a three-dimensional visualization that includes a visualization of a fabricated substrate may be generated based on an underlying structural model in the form of voxels. However, it should be understood that, in some embodiments, non-voxel based modeling methods may be used in conjunction with the techniques disclosed herein.

[0024] “Input Process Parameter” as used herein refers to knobs of a virtual fabrication process that may be modified. Examples include behavior parameter like etch rate, etch depth, deposition thickness, CMP over polish amount and etc., physical model parameters like gas flow species, gas flow rates, temperature, pressure, RF power, frequency, or the like. Each input process parameter may be defined by one or more values. In some embodiments, an inputprocess parameter is a single value, e.g., a temperature. In other embodiments, an input process parameter may be defined by a function or series of values, e.g., RF power as a function of time or RF power that changes at various set points during a fabrication process.

[0025] In various embodiments disclosed herein, input process parameters may be received via a user interface. In embodiments where input process parameters are received, the input process parameters may be used to simulate a fabrication process. In some embodiments, multiple input process parameter values may be received for a single input process parameter. For example, two values may be received that define a top and a bottom range of input process parameter values to simulate. In some embodiments, more than two values may be received for a single input process parameter. In some embodiments, one or more values received may define a set point for the input process parameter while other input process parameters are varied. As discussed further below, the high dimensionality of input process parameters may make it desirable to provide a simplified method of simulating various input process parameter values.

[0026] In some embodiments, three or more values may be received for each input process parameter. The lowest value and the highest value may define a window in which to simulate the input process parameter. The other input process parameter values received may define set points for the input process parameter while simulating a fabrication process over a different input process parameter changing within a different window based on received values for the other input process parameter.

[0027] “Output process Parameter” or “Output Parameter” as used herein refers to parameters or characteristics of a fabricated substrate. Examples include CD, bow CD, etch depth, bow location, or the like. In some embodiments, output process parameters may include those that may be measured using metrology techniques or virtual metrology techniques. In some embodiments, output process parameters may be virtual metrology data.

[0028] In various embodiments disclosed herein, output process parameters may be received via a user interface. In embodiments where output process parameters are received, the output process parameters may first be translated into input process parameters to be used to simulate a fabrication process. For example, based on received output process parameters, a trained model may determine input process parameter values that, when used to simulate a fabrication process, will result in a simulated fabricated substrate having the received output process parameters. In some embodiments, multiple output process parameter values may be received for a single input process parameter. For example, two values may be received that define a top and a bottom range of output process parameter values to simulate. In some embodiments, more than two values may be received for a single output process parameter. In someembodiments, one or more values received may define a set point for the output process parameter while other output process parameters are varied. As discussed further below, the high dimensionality of output process parameters may make it desirable to provide a simplified method of simulating various output process parameter values.

[0029] ‘ ‘Process Parameter” as used herein may refer to either or both of input process parameter and output process parameter.

[0030] ‘ ‘Virtual metrology data” as used herein refers to data produced, at least in part, by measuring features of a simulated fabricated substrate or reaction chamber in which the simulated substrate is processed or by a trained model. Virtual metrology data may include values for one or more characteristics of a simulated fabricated substrate, such as a CD, a bow CD, a depth, a bow location, etc. In some embodiments, virtual metrology data may substantially correspond to or match (or be within a predetermined range of) output process parameters received via a user interface, when such output process parameters are used to define a simulation of a fabrication process. In some embodiments, virtual metrology data may reflect metrology data that could be collected if a similar process were performed with a physical substrate and process chamber. For example, virtual metrology data may be similar to metrology data that could be produced by a metrology system performing microscopy (e.g., scanning electron microscopy (SEM), transmission electron microscopy (TEM), scanning transmission electron microscopy (STEM), reflection electron microscopy (REM), atomic force microscopy (AFM)) or optical metrology on a physical substrate. This may facilitate verification of virtual metrology data by matching it to physical metrology data that can be collected during or after a real / physical fabrication process.

[0031] In some embodiments, virtual metrology data may include 2D or 3D views of simulated fabricated substrates. A virtual fabrication environment may simulate a 3D structure of all devices and circuits. One or more views may be defined of the 3D structure. For example, a top-down or cross-sectional view may be defined, and a corresponding image generated for each simulated fabricated substrate. In some embodiments, the views may be user-defined views. These views may be supplemented with additional virtual metrology data, e.g., a cross- sectional view of an etch fabrication process that shows the fully etched feature may be supplemented or associated with information about a critical dimension at the top of the etched feature and a depth of the etched feature.

[0032] Machine learning model - A machine learning model is a trained computational model that takes parameter values and outputs results. Examples of machine learning models include random forests models, including deep random forests, neural networks, including recurrentneural networks and convolutional neural networks, restricted Boltzmann machines, recurrent tensor networks, Gaussian process models, and gradient boosted trees.

[0033] In the art, some machine learning models are characterized as “deep learning” models. Unless otherwise specified, any reference to “machine learning” herein includes deep learning embodiments. A deep learning model may be implemented in various forms such as by a neural network (e.g., a convolutional neural network), etc. In general, though not necessarily, it includes multiple layers. Each such layer includes multiple processing nodes, and the layers process in sequence, with nodes of layers closer to the model input layer processing before nodes of layers closer to the model output. In various embodiments, one layer feeds to the next, etc. In some implementations, a deep learning model is a model that takes process parameter data with very little preprocessing and outputs a simulated fabricated substrate and / or virtual metrology data. In some embodiments, the model has more than two (or more than three or more than four or more than five) layers of processing nodes that receive values from preceding layers (or as direct inputs) and that output values to succeeding layers (or the final output). Interior nodes are often “hidden” in the sense that their input and output values are not visible outside the model. In various embodiments, the operation of the hidden nodes is not monitored or recorded during operation.

[0034] In various implementations, the node layers may collectively form a neural network, although many deep learning models have other structures and formats. Some embodiments of deep learning models do not have a layered structure, in which case the above characterization of “deep” as having many layers is not relevant.

[0035] In some embodiments, a trained model may be a “forward” model. A forward model may be used to generate virtual metrology data based on provided input process parameter values. The forward model may be trained to represent a mapping between input process parameter values and virtual metrology data. A trained model may be a forward model that represents a function Y = f (X), such that given input process parameter values (e.g., temperature, pressure, gas flow rate, etc.), output values for a set of output process parameters (e.g., CD, bow CD, etch depth, etc.) may be predicted.

[0036] In some embodiments, a trained model may be a “backwards” model. A backwards model may be used to generate input process parameter values based on output process parameter values. A backwards model may take, as input, a user-specified output process parameter values Y and directly predict process parameter values X that correspond to the user- specified target values Y. A trained model may be a backwards model that represents a function X = g (Y), such that given output process parameter values (e.g., CD, bow CD, etch depth, etc.),input process parameter values that may be used to achieve the given output process parameter values may be predicted (e.g., temperature, pressure, gas flow rate, etc.).

[0037] In some implementations, a trained model that translates between values of output process parameter values (e.g., CD, bow CD, depth, bow location, etc.) and input process parameter values may be trained using data from a DoE-based simulation of a given fabrication process associated with the trained model. In particular, a set of target output characteristics or parameters may be identified, such as CD, bow CD, depth, bow location, etc. The fabrication process may be simulated multiple times using different process parameter values for each simulation. Examples of input process parameters may include gas flow rate, pressure, temperature, etc., and a process parameter value for a given process parameter corresponds to a value for that process parameter (e.g., a process chamber pressure of 1 Torr, or the like). The values of the input process parameters may be selected using a DoE technique to ensure that input process parameter values are selected using statistical techniques that optimally identify process parameter values that will ensure the full solution space is explored via the multiple simulations of the fabrication process. Note that the fabrication process may be simulated using a simulation that runs in a virtual fabrication engine, and may be a physics-based model and / or behavioral model of the fabrication process. Each simulation may take tens of seconds or minutes to run.

[0038] After the multiple simulations of the fabrication process, the trained model may be generated. For example, the model may be trained using a training set that includes a set of training samples. Each training sample may include a set of input process parameter values and the corresponding output process parameter values that were obtained when the simulation of the fabrication process was run using the set of input process parameter values. Note that, for each simulation run, the output process parameter values may be obtained using virtual metrology techniques (e.g., within the virtual fabrication engine). The model may have any suitable architecture, which may include one or more neural networks or other machine learning architectures. As another example, the model may be a regression model. Any suitable machine learning training technique may be utilized to train the model using the training set.

[0039] As described above, once the model has been trained, the trained model may be used to generate virtual metrology data without utilizing the simulation of the fabrication process directly, because the trained model has learned a mapping between input process parameter values and output process parameter values. Note that virtual metrology data generated from user-specified output process parameter values is generally substantially similar to or close to in value to the user- specified output process parameter values. The difference between virtualmetrology data and user- specified output process parameter values may depend on the accuracy in training of the trained models. Using a trained model to generate virtual metrology data instead of a behavioral- or physics-based simulation may reduce the computational complexity to generate virtual metrology data.

[0040] In some embodiments, a trained model may be provided as a script or other executable. In some embodiments, the script or executable may be packaged in a library and / or a fabrication process simulation algorithm (e.g., a behavioral or physics-based simulation of the fabrication process). Using the library, a user may be able to specify input process parameter values for a set of input process parameters and generate virtual metrology data. Using the library, a user may also be able to specify target output process parameter values for a set of output process parameters and identify input process parameter values that most closely correspond to the output process parameter values. The library may also be used to simulate the fabrication process using the process parameter values. In some embodiments, the library may be provided as a customized Python library or module, although other languages or environments may be additionally or alternatively used.

[0041] A “Graphical User Interface,” “GUI,” or “user interface” is a digital interface that a user may interact with and be updated based on input received. A GUI may receive input on parameters for a fabrication process to simulate or to retrieve virtual metrology data of already simulated fabrication processes. A GUI may be used to call a simulation algorithm or a trained model to generate virtual metrology data as described herein based on provided process parameters.

[0042] In some embodiments, a user may use a user interface to access the contents of a library. For example, the user may enter process parameters (e.g., input process parameters or output process parameters.) and values for the process parameters. Entry of these parameters and values may cause a trained model to be run, which may entail identify input process parameter values, translate the input process parameter values to virtual metrology data using a trained model in the library, and displaying the virtual metrology data. In some embodiments, execution of a fabrication process simulation included in the library to generate a simulated fabricated substrate is performed. In some embodiments, contents of the library (e.g., one or more scripts packaged in the library) may be utilized to perform virtual metrology on the fabricated substrate to provide output process parameter values. These output process parameter values may allow the user to confirm that the output process parameter values of the fabricated substrate correspond to expected output process parameter values.OVERVIEW

[0043] Many semiconductor fabrication processes are highly dimensional, as 5, 10, 15, 20, or more parameters may be defined for a given fabrication process. This dimensionality makes fabrication processes complicated to simulate or model. However, accurate simulation of such fabrication processes are desirable and useful because they may allow a process engineer to accurately select process parameter values that will enable a resulting fabricated substrate to meet various output parameter values or specifications. For example, process parameter values may be selected to enable the resulting substrate to meet output parameter values or specifications for output parameters such as critical dimension (CD), bow CD, bow location, etch depth, or the like.

[0044] In addition to being difficult to model, simulations of such fabrication processes may be difficult to analyze and review. For example, a process engineer may want to review results of a depth of experiment (DOE) simulation. A process engineer may want to review results for various reasons, including reviewing DOE results to determine if a simulation or model is performing as expected or to understand how results may change with respect to changes of various process parameters. For 3 process parameters each having 5 different possible values, 125 different results are generated, which may be time-consuming to review and compare. As the number of process parameters and possible values for reach process parameter increases, the difficulty of reviewing results increases significantly, e.g., assuming ten different parameter values for each parameter, the number of results is 10n, where n is the number of different parameters. Thus, it is desirable to facilitate generation and / or review of results, particularly for higher dimensional process spaces.

[0045] Disclosed herein are techniques for optimizing fabrication process recipe development. In some embodiments, a graphical user interface is provided that allows a user, such as a process engineer, to view results of simulations of one or more fabrication processes. In some embodiments, the results may be two- or three-dimensional images of a resulting substrate after simulating one or more fabrication processes. In some embodiments, the results may be two- or three-dimensional charts plotting combinations of parameters, e.g., critical dimension as a function of pressure. In some embodiments, a process engineer may designated parameters, including input process parameters and output process parameters, for one or more trained models. Even with some level of automation, engineers routinely spend much time manually analyzing recipes to determine what recipe parameters to use.

[0046] Figure 1 illustrates an example of a system for generating and / or viewing results of a process simulation or trained model. A user-interface 102 may receive input from a user anddisplay virtual metrology data and interactive elements. Examples of user interfaces are illustrated in Figures 3-5B. User-interface 102 may receive requests for display of results corresponding to particular output process parameters or input process parameters. In some embodiments, a user may provide output process parameters that may be translated into input process parameters by input process parameter determination logic 104. Input process parameter determination logic 104 may include a trained model, such as a trained backwards model, that translated received output process parameters into input process parameters. In some embodiments, input process parameter determination logic 104 may also receive a selection of various input process parameters and determine multiple sets of input process parameters according to a DOE process.

[0047] The input process parameters may then be provided to a fabrication process simulation logic 106 and / or a trained model logic 105. Fabrication process simulation logic 106 may utilize the determined input process parameters to simulate a fabrication process. Fabrication process simulation logic 106 may include a virtual fabrication environment. Fabrication process simulation logic 106 may generate simulated fabricated substrates 110. In some embodiments, simulated fabricates substrates 110 may include virtual metrology data or voxels that may be used to determine virtual metrology data. In some embodiments, simulated fabricated substrates 110 may include a 1-, 2-, or 3-dimensional representation of simulated fabricated substrates.

[0048] Trained model logic 105 may generate virtual metrology data using a trained model, e.g., a forward model. A trained model may represent a mapping between input process parameter values and virtual metrology data. A trained model may be a forward model that represents a function Y = f (X), such that given input process parameter values (e.g., temperature, pressure, gas flow rate, etc.), output values for a set of output process parameters (e.g., CD, bow CD, etch depth, etc.) may be predicted. In some embodiments, multiple trained models may be available. In such embodiments, a request may specify which trained model to use. In some embodiments, different models may be trained for particular processes, e.g., different types of etch processes. In some embodiments, different models may be trained and usable. For example, different models may be trained for different tools that perform a process, e.g., a trained model for each of the Kiyo® and Flex® tools available from Fam Research. In other embodiments, different trained models may be trained on the same training data set with different hyperparameters.

[0049] Results viewer logic 108 may retrieve and / or generate virtual metrology from simulated fabricated substrates and virtual metrology data 110 and present it for display via the userinterface. In some embodiments, interactive elements may be displayed that may receive selections. For example, a slider for an output process parameter may be displayed, and a user may select from a discrete range of output process parameters, where each output process parameter in the range corresponds to a different simulated fabricated substrate. Virtual metrology data corresponding to the simulated fabricated substrate having the selected output process parameter may then be displayed. Changing the selection will change the virtual metrology data that is displayed.VIEWING VIRTUAL METROLOGY DATA

[0050] Figure 2 presents a flowchart for a process to view results corresponding to a simulated fabrication process as described herein. A request is received to display results of a simulated fabrication process (202). In some embodiments, the request is received via a user interface. In some embodiments, the request may include process parameter values for a set of process parameters, which may be either input process parameter values or output process parameter values. When the request includes input process parameter values, the input process parameter values may be used as input to a fabrication process simulation algorithm or a forward trained model to generate virtual metrology data, as discussed below. In some embodiments, when the request includes output process parameter values, the output process parameter values may be translated into input process parameter values using a backwards trained model, which may then be used as input process parameters as discussed above. It should be understood that virtual metrology data generated by a simulation algorithm or trained model may be different than the output process parameter values. In some embodiments, virtual metrology data that is based on output process parameter values is within about 10%, about 5%, about 1%, or about 0.5% of the output process parameter values. In some embodiments, a request may include output process parameter values that correspond to previously generated virtual metrology data, generated either by a fabrication process simulation algorithm or a trained model. In such embodiments, the output process parameter values in the request may be used to determine which sets of virtual metrology data to retrieve for display.

[0051] It should be noted that a trained model (e.g., trained using the techniques shown in and described above) may be a forward model that, given a set of input process parameter values, generates corresponding output process parameter values (e.g., given a set of input process parameter values, generates a corresponding CD, bow location, or the like). Additionally or alternatively, the trained model may be a backward model that, given a set of output process parameter values (e.g., CD, bow location, etch depth, etc.), generates input process parameter values that will yield, when simulated, the set of output process parameter values. As notedabove, in some embodiments multiple trained models may be available, e.g., multiple trained forward models, and a request may specify a trained model.

[0052] In some embodiments, the request may include a range of parameter values for each process parameter of a set of process parameters (including either input process parameters and / or output process parameters). The range of parameter values may represent a process window that is desired to be modelled and / or simulated. In some embodiments, a baseline parameter value may also be provided in addition to a range of parameter values. In such embodiments, the baseline parameter value may represent a constant value for a process parameter to be used while varying the value of a different process parameter, e.g., holding temperature and pressure constant at baseline parameter values while RF power is varied.

[0053] In some embodiments, the request may include a view of a 3-dimensional simulated fabricated substrate. In some embodiments, a user-interactable 3-dimensional rendering of a simulated fabricated substrate is displayed. In some embodiments, a user may select the view of a simulated fabricated substrate to be displayed. The user-selected view may be used to generate views for each simulated fabricated substrate. In some embodiments, the view is part of the request received via a user interface. In some embodiments, each view may be saved as an image to a log file or other data storage. This may improve responsiveness of the user interface as each image can be quickly retrieved and displayed to a user. Rendering and displaying a fully interactive 3D model may take several seconds, e.g., at least 5 seconds or at least 10 seconds, whereas loading a new image can be performed in milliseconds or less. This problem may be particularly notable when interacting with highly dimensional data, as noted above, where more than about 100 simulated fabricated substrates are available for rendering and display. Rendering and displaying each simulated fabricated substrate is computationally intensive, particularly compared to displaying a pre-selected view that may be saved as, e.g., a single image for each simulated fabricated substrate.

[0054] In an optional embodiment, a simulation of the fabrication process is performed based on the request (204). In some embodiments, a design of experiments (DoE) simulation of the fabrication process is performed, where the DoE simulation was designed to simulate or cover a solution space of the fabrication process based on the parameter values in the request. The received parameter values may define a solution space, and values of the input process parameters may be selected using a DoE technique to ensure that input process parameter values are selected using statistical techniques that optimally identify input process parameter values that will ensure the full solution space is explored via the multiple simulations of the fabrication process. Note that the fabrication process may be simulated using a simulation thatruns in a virtual fabrication engine, and may be a physics-based model and / or behavioral model of the fabrication process. Each simulation may take tens of seconds or minutes to run.

[0055] While block 204 performs a simulation based on the request, in some embodiments, a simulation may already have been performed. In such embodiments, a request may pertain to viewing virtual metrology data for a previously simulated set of simulated fabricated substrates. In such embodiments, the set of simulated fabricated substrates may have corresponding virtual metrology data and / or input process parameter values. A request may correspond to the set or a subset of the set of simulated fabricated substrates based on the process parameters included in the request.

[0056] Virtual metrology data is generated (206), and an interactive GUI displaying virtual metrology data is provided (208). Virtual metrology data may be generated based on the information included in the request. In some embodiments, virtual metrology data may be generated from simulated fabricated substrates. In some embodiments, virtual metrology data may include images. Images may be generated by exporting a 3-dimensional view of a previously simulated fabricated substrate, e.g., generated in block 204 or earlier. Figures 4A- B illustrate an example 3-dimensional view of a simulated fabricated substrate. In some implementations, virtual metrology data may include one or more charts that illustrate various relationships between input process parameters and output process parameters or between various output process parameters. Figures 5A-B illustrate example charts between input process parameters and output process parameters.

[0057] In some embodiments, the virtual metrology data is generated by providing input process parameter values to a physics-based model and / or behavioral model of the fabrication process as noted above in block 204. In some embodiments, the virtual metrology data is generated by providing input process parameter values to a trained model. A trained model may generate virtual metrology data much faster than a full physics-based model and / or behavioral model of the fabrication process. For example, a trained model may generate virtual metrology data for a process window of different parameters in less than a minute, compared to each simulation of a set of input process parameter values taking tens of seconds or minutes to run. In some embodiments, a trained model may be a forward model.

[0058] The interactive GUI may include one or more interactive elements for receiving input, e.g., a selection of a process parameter value (210). A user may use the interactive elements to select a different process parameter value. Based on the input, the GUI is updated to display different virtual metrology data (212). For example, a different image of a simulated fabricated substrate corresponding to the selected process parameter value is displayed. The selection maybe repeatedly changed to view different virtual metrology data corresponding to different simulated fabricated substrates. In some embodiments, the virtual metrology data displayed is generated based on a trained model rather than a simulated fabricated substrate, however the virtual metrology data displayed may still change to correspond to a selection of various process parameters values.

[0059] Figure 3 presents an example user interface 300 for receiving a request to display virtual metrology data and generating virtual metrology data for display. Process parameters 302 indicate different process parameters. In the example of Figure 3, the process parameters 302 are output process parameters representing top critical dimension (TCD), sigma, and depth. These are output process parameters as they represent virtual metrology data of simulated fabricated substrates. Split ranges 304 are also received, indicating a minimum and maximum value for each input parameter 302. These ranges may be used to define a process window for virtual metrology data to be displayed. For example, the range of process parameter values for “depth” in the example of Figure 3 is 100 to 300. These ranges may be provided to a trained model as described above that may generate various sets of input process parameters based on DoE techniques to ensure the full solution space is explored for the provided ranges.

[0060] A 3D viewer may also be used to select a particular 3-dimensional view of each simulated fabricated substrate. Figure 4A presents an example view 401. A user may manipulate a sample view to select a particular cross-section to view for each simulated fabricated substrate. In some embodiments, a user may wish to view a particular feature of a simulated fabricated substrate at a particular cross-section. A generate element 308 may be used to execute a script based on the provided process parameters and selected view. In some embodiments, other parameters may be specified by a user. In some embodiments, user interface 300 may include a user interface control, such as a push button, that may cause the virtual metrology data generation and display process to begin. In some embodiments, once the generation and display process has terminated, a visualization of the fabricated substrate (e.g., a three-dimensional visualization) may be presented along with user-interactable elements to view virtual metrology data from different sets of virtual metrology data. Additionally or alternatively, in some embodiments, virtual metrology data associated with the fabricated substrate may be presented (e.g., via a user interface) and / or saved (e.g., a log file).

[0061] Figure 4A presents an example user interface 400 for displaying virtual metrology data. User interface 400 may be generated based on input parameters as shown in Figure 3, particularly displaying virtual metrology data for different combinations of depth, sigma, and TCD. A view 401 may provide a 3-dimensional image showing a feature of a simulatedfabricated substrate. Interactive elements 404a-c present discrete ranges of values for each of depth, sigma, and TCD. In the embodiment of Figure 4A, moving each slider would update view 401 to display a different simulated fabricated substrate having corresponding virtual metrology data.

[0062] Notably, the interactive elements 404a-c represent discrete combinations of values for each of depth, sigma, and TCD. In some embodiments, a user may not arbitrarily select combinations of depth, sigma, and TCD, rather, a user may step through combinations of virtual metrology data that correspond to simulated substrates. For example, assuming ten different values for each of depth, sigma, and TCD, the interactive elements 404a-c permit a user to view virtual metrology data corresponding to one of 1000 different simulated substrates. The interactive elements 404a-c facilitate reviewing these results by receiving input and updating the displayed virtual metrology data to correspond to the selected combinations of process parameters.

[0063] Figure 4B presents 3 different views according to different positions of the slider element for depth. Views 410a-c correspond to different values for depth sliders 414a-c. When a selection of a depth is received, e.g., depth 414b, the virtual metrology data displayed is updated, e.g., view 410b is displayed. Thus, a process engineer or other users may quickly view virtual metrology data for different output process parameter values by selecting different output process parameter values via interactive elements. In some embodiments, a view is saved for all available combinations of process parameters, and selecting a different process parameter changes the displayed view without needing to generate new virtual metrology data. This may dramatically speed up review of simulated fabricated substrates as the virtual metrology data to be displayed is generated prior to displaying, facilitating faster review than running a simulation for each selection.

[0064] Figures 3 and 4A-B are directed to an embodiment of receiving output process parameters and displaying interactive elements that receive selections of output process parameters. However, in some embodiments, input process parameters may be received and interactive elements displayed may be ranges of input process parameters. In such embodiments, a DoE technique may still be used to vary input process parameter values within ranges received for each input process parameter.

[0065] Figures 5A-B present another example embodiment of an implementation for displaying virtual metrology data based on received input. In Figures 5A-B, a trained model 502 may be used to generate virtual metrology data based on process parameter values. In some embodiments, a user selection of one of a plurality of trained models may be used. A requestas described in block 202, above, may include a trained model to be used for generating virtual metrology data.

[0066] Process parameters 508 may be input process parameters or output process parameters. In some embodiments, each process parameter may be defined by a range, i.e., a minimum and maximum value, and optionally a baseline value. A baseline value 509 may be used to reduce the dimensionality of the process window for generating virtual metrology data. When generating virtual metrology data, one or more process parameters may be held at a baseline value while other process parameters change within the defined range. In some embodiments, one process parameter value is varied within a received range, while all other process parameter values are fixed at a baseline value. Baseline values may be user- selected. Baseline set 504 may be used to select from pre-determined baseline values. In some embodiments, baseline value sets may be generated by process engineers or other users. Baseline values may help reduce dimensionality by varying one process parameter value while fixing other process parameter values. The resulting virtual metrology data may then be easily presented in charts that illustrate changes in virtual metrology data as a function of a single variable with other process parameters are simulated or modeled as constants.

[0067] For example, a range of pressure for a simulated fabrication process may be between 1 Torr and 10 Torr, with a baseline value of 5 Torr, and a duration of a gas flow may be between 0.1 seconds and 4 seconds, with a baseline value of 2.5 seconds. When generating virtual metrology data using a simulation algorithm or trained model, the pressure baseline value of 5 Torr may be held constant while the duration of gas flow is varied within the range of 0.1 seconds to 4 seconds according to a DOE technique. Conversely, the duration of gas flow may be held constant at 2.5 seconds while the pressure is varied within the range of 1 Torr to 10 Torr according to a DOE technique. Virtual metrology data may be generated for each set of parameter values. Virtual metrology data may then be charted as a function of the changing process parameter while other process parameters are held constant at baseline values. Sensitivity plots 510 illustrate three rows of charts for different virtual metrology data as functions of each process parameter. In some embodiments, virtual metrology data that is generated may be used to generate various charts or other visualizations. In some embodiments, virtual metrology data may be saved to a log file.

[0068] Figure 5A presents sensitivity plots 510 that illustrate virtual metrology data as functions of process parameters. Figure 5B presents contour maps 512 that illustrate relationships between multiple process parameters and virtual metrology data. For example, virtual metrology data may be charted as a contour map on a graph of two different processparameters. In some embodiments, the contour maps 512 of Figure 4B are an alternative visualization of the relationship between process parameters than charts 510 of Figure 5A. User-selectable elements 506 and 507 may receive input from a user to change the displayed information between sensitivity plots 510 and contour maps 512. While sensitivity plots 510 and contour maps 512 are shown in Figures 5A-B, in some embodiments other visualizations of data may be presented. For example, a view of a wafer may be generated similar to example view 401. The visualizations described herein are not limiting and various methods of visualizing data may be used to present information on a user-interface.CONTEXT FOR DISCLOSED COMPUTATIONAL EMBODIMENTS

[0069] Systems including fabrication tools as described herein may include logic for process simulations.

[0070] The analysis logic may be designed and implemented in any of various ways. For example, the logic can be implemented in hardware and / or software. Examples are presented in the controller section herein. Hardware-implemented control logic may be provided in any of a variety of forms, including hard coded logic in digital signal processors, applicationspecific integrated circuits, and other devices that have algorithms implemented as hardware. Analysis logic may also be implemented as software or firmware instructions configured to be executed on a general-purpose processor. System control software may be provided by “programming” in a computer readable programming language.

[0071] The computer program code for controlling processes in a process sequence can be written in any conventional computer readable programming language: for example, assembly language, C, C++, Pascal, Fortran, Python, or others. Compiled object code or script is executed by the processor to perform the tasks identified in the program. Also as indicated, the program code may be hard coded.

[0072] Integrated circuits used in logic may include chips in the form of firmware that store program instructions, digital signal processors (DSPs), chips defined as application specific integrated circuits (ASICs), and / or one or more microprocessors, or microcontrollers that execute program instructions (e.g., software). Program instructions may be instructions communicated in the form of various individual settings (or program files), defining operational parameters for carrying out a particular analysis or image analysis application.

[0073] Figure ? is a block diagram of an example of the computing device 700 suitable for use in implementing some embodiments of the present disclosure. For example, device 700 may be suitable for implementing some or all functions for translating between inputs and target outputs or vice versa, performing process simulations, or the like.

[0074] Computing device 700 may include a bus 702 that directly or indirectly couples the following devices: memory 704, one or more central processing units (CPUs) 706, one or more graphics processing units (GPUs) 708, a communication interface 710, input / output (I / O) ports 712, input / output components 714, a power supply 716, and one or more presentation components 718 (e.g., display(s)). In addition to CPU 706 and GPU 708, computing device 700 may include additional logic devices that are not shown in Figure 7, such as but not limited to an image signal processor (ISP), a digital signal processor (DSP), an ASIC, an FPGA, or the like.

[0075] Although the various blocks of Figure 7 are shown as connected via the bus 702 with lines, this is not intended to be limiting and is for clarity only. For example, in some embodiments, a presentation component 718, such as a display device, may be considered an VO component 714 (e.g., if the display is a touch screen). As another example, CPUs 706 and / or GPUs 708 may include memory (e.g., the memory 704 may be representative of a storage device in addition to the memory of the GPUs 708, the CPUs 706, and / or other components). In other words, the computing device of Figure 7 is merely illustrative. Distinction is not made between such categories as “workstation,” “server,” “laptop,” “desktop,” “tablet,” “client device,” “mobile device,” “hand-held device,” “electronic control unit (ECU),” “virtual reality system,” and / or other device or system types, as all are contemplated within the scope of the computing device of Figure 7.

[0076] Bus 702 may represent one or more busses, such as an address bus, a data bus, a control bus, or a combination thereof. The bus 702 may include one or more bus types, such as an industry standard architecture (ISA) bus, an extended industry standard architecture (EISA) bus, a video electronics standards association (VESA) bus, a peripheral component interconnect (PCI) bus, a peripheral component interconnect express (PCIe) bus, and / or another type of bus.

[0077] Memory 704 may include any of a variety of computer-readable media. The computer- readable media may be any available media that can be accessed by the computing device 700. The computer-readable media may include both volatile and nonvolatile media, and removable and non-removable media. By way of example, and not limitation, the computer-readable media may comprise computer-storage media and / or communication media.

[0078] The computer- storage media may include both volatile and nonvolatile media and / or removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, and / or other data types. For example, memory 704 may store computer-readable instructions (e.g.,that represent a program(s) and / or a program element(s), such as an operating system. Computer-storage media may include, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by computing device 700. As used herein, computer storage media does not comprise signals per se.

[0079] The communication media may embody computer-readable instructions, data structures, program modules, and / or other data types in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. The term “modulated data signal” may refer to a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, the communication media may include wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared and other wireless media. Combinations of any of the above should also be included within the scope of computer- readable media.

[0080] CPU(s) 706 may be configured to execute the computer-readable instructions to control one or more components of the computing device 700 to perform one or more of the methods and / or processes described herein. CPU(s) 706 may each include one or more cores (e.g., one, two, four, eight, twenty-eight, seventy-two, etc.) that are capable of handling a multitude of software threads simultaneously. CPU(s) 706 may include any type of processor and may include different types of processors depending on the type of computing device 700 implemented (e.g., processors with fewer cores for mobile devices and processors with more cores for servers). For example, depending on the type of computing device 700, the processor may be an ARM processor implemented using Reduced Instruction Set Computing (RISC) or an x86 processor implemented using Complex Instruction Set Computing (CISC). Computing device 700 may include one or more CPUs 706 in addition to one or more microprocessors or supplementary co-processors, such as math co-processors.

[0081] GPU(s) 708 may be used by computing device 700 to render graphics (e.g., 3D graphics). GPU(s) 708 may include many (e.g., tens, hundreds, or thousands) of cores that are capable of handling many software threads simultaneously. GPU(s) 708 may generate pixel data for output images in response to rendering commands (e.g., rendering commands from CPU(s) 706 received via a host interface). GPU(s) 708 may include graphics memory, such as display memory, for storing pixel data. The display memory may be included as part of memory704. GPU(s) 708 may include two or more GPUs operating in parallel (e.g., via a link). When combined, each GPU 708 can generate pixel data for different portions of an output image or for different output images (e.g., a first GPU for a first image and a second GPU for a second image). Each GPU can include its own memory or can share memory with other GPUs.

[0082] In examples where the computing device 700 does not include the GPU(s) 708, the CPU(s) 706 may be used to render graphics.

[0083] Communication interface 710 may include one or more receivers, transmitters, and / or transceivers that enable computing device 700 to communicate with other computing devices via an electronic communication network, included wired and / or wireless communications. Communication interface 710 may include components and functionality to enable communication over any of a number of different networks, such as wireless networks (e.g., Wi-Fi, Z-Wave, Bluetooth, Bluetooth LE, ZigBee, etc.), wired networks (e.g., communicating over Ethernet), low-power wide-area networks (e.g., LoRaWAN, SigFox, etc.), and / or the internet.

[0084] I / O ports 712 may enable the computing device 700 to be logically coupled to other devices including I / O components 714, presentation component(s) 718, and / or other components, some of which may be built in to (e.g., integrated in) computing device 700. Illustrative I / O components 714 include a microphone, mouse, keyboard, joystick, track pad, satellite dish, scanner, printer, wireless device, etc. I / O components 714 may provide a natural user interface (NUI) that processes air gestures, voice, or other physiological inputs generated by a user. In some instances, inputs may be transmitted to an appropriate network element for further processing. An NUI may implement any combination of speech recognition, stylus recognition, facial recognition, biometric recognition, gesture recognition both on screen and adjacent to the screen, air gestures, head and eye tracking, and touch recognition (as described in more detail below) associated with a display of computing device 700. Computing device 700 may be include depth cameras, such as stereoscopic camera systems, infrared camera systems, RGB camera systems, touchscreen technology, and combinations of these, for gesture detection and recognition. Additionally, computing device 700 may include accelerometers or gyroscopes (e.g., as part of an inertia measurement unit (IMU)) that enable detection of motion. In some examples, the output of the accelerometers or gyroscopes may be used by computing device 700 to render immersive augmented reality or virtual reality.

[0085] Power supply 716 may include a hard-wired power supply, a battery power supply, or a combination thereof. Power supply 716 may provide power to computing device 700 to enable the components of computing device 700 to operate.

[0086] Presentation component(s) 718 may include a display (e.g., a monitor, a touch screen, a television screen, a heads-up-display (HUD), other display types, or a combination thereof), speakers, and / or other presentation components. Presentation component(s) 718 may receive data from other components (e.g., GPU(s) 708, CPU(s) 706, etc.), and output the data (e.g., as an image, video, sound, etc.).

[0087] The disclosure may be described in the general context of computer code or machine- useable instructions, including computer-executable instructions such as program modules, being executed by a computer or other machine, such as a personal data assistant or other handheld device. Generally, program modules including routines, programs, objects, components, data structures, etc., refer to code that perform particular tasks or implement particular abstract data types. The disclosure may be practiced in a variety of system configurations, including hand-held devices, consumer electronics, general-purpose computers, more specialty computing devices, etc. The disclosure may also be practiced in distributed computing environments where tasks are performed by remote-processing devices that are linked through a communications network.Conclusion

[0088] Although the foregoing embodiments have been described in some detail for purposes of clarity of understanding, it will be apparent that certain changes and modifications may be practiced within the scope of the appended claims. Embodiments disclosed herein may be practiced without some or all of these specific details. In other instances, well-known process operations have not been described in detail to not unnecessarily obscure the disclosed embodiments. Further, while the disclosed embodiments will be described in conjunction with specific embodiments, it will be understood that the specific embodiments are not intended to limit the disclosed embodiments. It should be noted that there are many alternative ways of implementing the processes, systems, and apparatus of the present embodiments. Accordingly, the present embodiments are to be considered as illustrative and not restrictive, and the embodiments are not to be limited to the details given herein.

Claims

CLAIMSWhat is claimed is:

1. A method, comprising: receiving, via a user interface, a user-specified set of process parameters associated with a fabrication process and a range of process parameter values for each process parameter of the set of process parameters; and displaying, via the user interface, interactive elements that may receive a selection of a process parameter value of the range of process parameter values for each process parameter; receiving, via the user interface, a selection of a process parameter value for each process parameter; and updating the user interface to display virtual metrology data corresponding to the selection of process parameter values.

2. The method of claim 1, wherein the process parameters are input process parameters.

3. The method of claim 1, wherein the process parameters are output process parameters.

4. The method of claim 3, further comprising determining input process parameter values based on the output process parameter values, wherein the virtual metrology data is based on the input process parameter values.

5. The method of claim 3, further comprising determining the input process parameter values by providing the output process parameter values to a trained model that represents a function that associates output process parameter values to input process parameter values such that a simulation of a fabrication process using the input process parameter values yields a simulated fabricated substrate having virtual metrology data that is substantially similar to the output process parameter values.

6. The method of claim 3, wherein a virtual metrology data corresponding to an output process parameter value is within about 10% of the output process parameter value.

7. The method of claim 1, further comprising: simulating the fabrication process using a first set of process parameter values by using a fabrication process simulation algorithm, wherein the first set of process parameter values corresponds to the selection of process parameter values, wherein the virtual metrology data is based on the simulation.

8. The method of claim 1, wherein the range of process parameter values are used to perform a design of experiments (DoE) simulation of a fabrication process designed to simulate a solution space of the fabrication process.

9. The method of claim 1, wherein the virtual metrology data comprises an image of a 3-dimensional rendering of a simulated fabricated substrate generated by a simulated fabrication process, the simulated fabrication process performed based on the selection of process parameter values.

10. The method of claim 9, further comprising: displaying, via the user interface, a user-manipulable view of the 3-dimensional rendering of the simulated fabricated substrate, and receiving, via the user interface, a selection of the view of the 3-dimensional rendering, wherein the image of the 3-dimensional rendering of the simulated fabricated substrate is based on the selection of the view.

11. The method of claim 1 , further comprising: receiving, via the user interface, an updated selection of a process parameter value for each process parameter; and updating the user interface to display updated virtual metrology data corresponding to the updated selection of process parameter values.

12. The method of claim 1, wherein the set of process parameters comprises at least 3 different process parameters.

13. The method of claim 1, wherein the fabrication process comprises an etching process or a deposition process.

14. A non-transitory computer-readable medium comprising computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising: receiving, via a user interface, a user-specified set of process parameters associated with a fabrication process and a range of process parameter values for each process parameter of the set of process parameters; and displaying, via the user interface, interactive elements that may receive a selection of a process parameter value of the range of process parameter values for each process parameter; receiving, via the user interface, a selection of a process parameter value for each process parameter; and updating the user interface to display virtual metrology data corresponding to the selection of process parameter values.

15. A method, comprising: receiving, via a user interface, a user-specified set of input process parameters associated with a fabrication process and a baseline process parameter value for each process parameter of the set of input process parameters; generating virtual metrology data based on the baseline process parameter values and the set of input process parameters, wherein a first set of virtual metrology data is generated based on a first range of process parameter values for a first input process parameter of the set of input process parameters and the baseline process parameter values for input process parameters of the set of input process parameters that are not the first input process parameter; and displaying, via the user interface, the virtual metrology data.

16. The method of claim 15, wherein the virtual metrology data comprises one or more charts of virtual metrology data as a function of the first input process parameter.

17. The method of claim 15, further comprising receiving, via the user interface, the first range of process parameter values for the first input process parameter.

18. The method of claim 15, further comprising generating the virtual metrology data by providing the baseline process parameter value for each process parameter and the first 1range of process parameter values to a trained model, wherein the model has been trained to predict virtual metrology data based on process parameter values.

19. The method of claim 18, further comprising receiving, via the user interface, a selection of the trained model to generate the virtual metrology data from a plurality of trained models.

20. The method of claim 18, wherein the trained model comprises a trained neural network.

21. The method of claim 18, wherein the trained model was trained using a design of experiments (DoE) simulation of the fabrication process designed to simulate a solution space of the fabrication process.

22. The method of claim 15, wherein the fabrication process comprises an etching process or a deposition process.

23. A non-transitory computer-readable medium comprising computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising: receiving, via a user interface, a user-specified set of input process parameters associated with a fabrication process and a baseline process parameter value for each process parameter of the set of input process parameters; generating virtual metrology data based on the baseline process parameter values and the set of input process parameters, wherein a first set of virtual metrology data is generated based on a first range of process parameter values for a first input process parameter of the set of input process parameters and the baseline process parameter values for input process parameters of the set of input process parameters that are not the first input process parameter; and displaying, via the user interface, the virtual metrology data.

Images