# US 11,029,605 B2 · Optimization based on machine learning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,029,605 B2 - Document ID: US11029605B2 - Status: Granted - Kind: B2 - Application number: 16/527,098 - Filed: 2019-07-31 - Published: 2019-11-21 - Granted: 2021-06-08 - Earliest claimed: 2014-12-15 - Assignees: ASML Netherlands B.V. - Applicants: ASML Netherlands B.V. - Inventors: Xiaofeng Liu - Web page: https://patentgrep.com/patent/US11029605B2 ## CPC - G03F 7/70125: {Use of illumination settings tailored to particular mask patterns (details of setting means G03F7/70091)} - G03F 7/70441: {Optical proximity correction [OPC]} - G03F 7/70491: {Information management, e.g. software; Active and passive control, e.g. details of controlling exposure processes or exposure tool monitoring processes} - G06F 30/00: Computer-aided design [CAD] - G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) - G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model - G06N 20/00: Machine learning - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - G03F: PHOTOMECHANICAL PRODUCTION OF TEXTURED OR PATTERNED SURFACES, e.g. FOR PRINTING, FOR PROCESSING OF SEMICONDUCTOR DEVICES; MATERIALS THEREFOR; ORIGINALS THEREFOR; APPARATUS SPECIALLY ADAPTED THEREFOR; (phototypographic composing devices B41B; photosensitive materials or processes for photographic purposes G03C; electrophotography, sensitive layers or processes therefor G03G) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method for improving a lithographic process for imaging a portion of a design layout onto a substrate using a lithographic apparatus, the method including: obtaining a first source of the lithographic apparatus; classifying the first source into a class among a plurality of possible classes, based on one or more numerical characteristics of the first source, using a machine learning model, by a computer; determining whether the class is among one or more predetermined classes; only when the class is among the one or more predetermined classes, adjusting one or more source design variables to obtain a second source. ## Claims ### Claim 1 A method for improving a lithographic process for imaging a portion of a design layout onto a substrate using a lithographic apparatus, the method comprising: obtaining an illumination source that is in one or more predetermined classes among a plurality of possible classes, as determined, based on one or more numerical characteristics of the illumination source, by a machine learning model, the machine learning model developed on illumination source numerical characteristics in order to classify illumination sources; and optimizing, by a hardware computer system, the illumination source for imaging the portion of the design layout by adjusting one or more illumination source design variables. ### Claim 2 (depends on 1) The method of claim 1, wherein the machine learning model is trained with a training set comprising elements of feature vectors and classes of the feature vectors, wherein the feature vectors comprise one or more numerical characteristics of an illumination source for a lithographic apparatus. ### Claim 3 (depends on 1) The method of claim 1, wherein the obtaining further comprises obtaining the illumination source by randomly selecting a point in a space of the one or more illumination source design variables. ### Claim 4 (depends on 3) The method of claim 3, comprising obtaining the illumination source by a Monte-Carlo method. ### Claim 5 (depends on 1) The method of claim 1, further comprising optimizing another parameter of the lithographic process by adjusting one or more non-source design variables. ### Claim 6 (depends on 1) The method of claim 1, further comprising optimizing the illumination source together with the portion of the design layout. ### Claim 7 (depends on 1) The method of claim 1, further comprising training the machine learning model using the optimized illumination source. ### Claim 8 A computer program product comprising a non-transitory computer readable medium having instructions therein, the instructions, upon execution by a hardware computer system, configured to cause the hardware computer system to at least: obtain an illumination source that is in one or more predetermined classes among a plurality of possible classes, as determined, based on one or more numerical characteristics of the illumination source, by a machine learning model, the machine learning model developed on illumination source numerical characteristics in order to classify illumination sources; and optimize the illumination source, by adjusting one or more illumination source design variables, for a lithographic process for imaging a portion of a design layout onto a substrate using a lithographic apparatus and the illumination source. ### Claim 9 (depends on 8) The computer program product of claim 8, wherein the machine learning model is trained with a training set comprising elements of feature vectors and classes of the feature vectors, wherein the feature vectors comprise one or more numerical characteristics of an illumination source for a lithographic apparatus. ### Claim 10 (depends on 8) The computer program product of claim 8, wherein the instructions configured to cause the hardware computer system to obtain the illumination source obtaining are further configured to cause the hardware computer system to obtain the illumination source by randomly selecting a point in a space of the one or more illumination source design variables. ### Claim 11 (depends on 10) The computer program product of claim 10, wherein the instructions configured to cause the hardware computer system to obtain the illumination source are further configured to cause the hardware computer system to obtain the illumination source by a Monte-Carlo method. ### Claim 12 (depends on 8) The computer program product of claim 8, wherein the instructions are further configured to cause the hardware computer system to optimize another parameter of the lithographic process by adjusting one or more non-source design variables. ### Claim 13 (depends on 8) The computer program product of claim 8, wherein the instructions are further configured to cause the hardware computer system to optimize the illumination source together with the portion of the design layout. ### Claim 14 (depends on 8) The computer program product of claim 8, wherein the instructions are further configured to cause the hardware computer system to train the machine learning model using the optimized illumination source. ### Claim 15 A computer program product comprising a non-transitory computer readable medium having instructions therein, the instructions, upon execution by a hardware computer system, configured to cause the hardware computer system to at least: obtain one or more numerical characteristics for each illumination source of a plurality of illumination sources, the illumination sources configured for imaging a portion of a design layout onto a substrate using a lithographic apparatus; obtain a designation of each illumination source of the plurality of illumination sources into a class among a plurality of possible classes; and train a machine learning model based on a training set comprising the one or more numerical characteristics of the illumination sources and the designated classes for the illumination sources, the trained machine learning model configured to classify an illumination source based on one or more illumination source numerical characteristics and the trained machine learning model for optimizing an illumination source, by adjustment of one or more illumination source design variables, for imaging a pattern. ### Claim 16 (depends on 15) The computer program product of claim 15, wherein the instructions are further configured to cause the hardware computer system to: calculate a value of a cost function from a certain illumination source of the plurality of illumination sources; and designate the class for the certain illumination source among the plurality of possible classes, based on the value of the cost function. ### Claim 17 (depends on 16) The computer program product of claim 16, wherein the instructions are further configured to cause the hardware computer system to adjust one or more non-source design variables before calculation of the value of the cost function. ### Claim 18 (depends on 15) The computer program product of claim 15, wherein the instructions are further configured to cause the hardware computer system to parameterize one or more illumination sources of the plurality of illumination sources so as to obtain the associated one or more numerical characteristics. ### Claim 19 (depends on 15) The computer program product of claim 15, wherein the instructions are further configured to cause the hardware computer system to obtain the plurality of illumination sources by randomly selecting points in a space of one or more illumination source design variables. ### Claim 20 (depends on 15) The computer program product of claim 15, wherein the plurality of possible classes consists of two classes and a class is designated from either of the two classes of the plurality of possible classes.