# US 2022/0285232 A1 · Controlling concentration profiles for deposited films using machine learning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2022/0285232 A1 - Document ID: US20220285232A1 - Status: Published application - Kind: A1 - Application number: 17/191,026 - Filed: 2021-03-03 - Published: 2022-09-08 - Earliest claimed: 2021-03-03 - Assignees: Applied Materials, Inc. - Applicants: Applied Materials, Inc. - Inventors: Anton V. Baryshnikov; Aykut Aydin; Zubin Huang; Rui Cheng; Yi Yang; Diwakar Kedlaya; Venkatanarayana Shankaramurthy; Krishna Nittala; Karthik Janakiraman - Web page: https://patentgrep.com/patent/US20220285232A1 ## CPC - H10P 74/238: {comprising acting in response to an ongoing measurement without interruption of processing, e.g. endpoint detection or in-situ thickness measurement} - C23C 14/542: {Controlling the film thickness or evaporation rate} - C23C 14/548: {Controlling the composition} - C23C 16/52: Controlling or regulating the coating process {(C23C16/45557, C23C16/279 take precedence)} - G05B 13/0265: {the criterion being a learning criterion} - G05B 13/048: {using a predictor} - G06N 3/08: Learning methods - G06N 20/00: Machine learning - H10P 72/0604: {Process monitoring, e.g. flow or thickness monitoring} - H10P: GENERIC PROCESSES OR APPARATUS FOR THE MANUFACTURE OR TREATMENT OF DEVICES COVERED BY CLASS H10 - C23C: COATING METALLIC MATERIAL; COATING MATERIAL WITH METALLIC MATERIAL; SURFACE TREATMENT OF METALLIC MATERIAL BY DIFFUSION INTO THE SURFACE, BY CHEMICAL CONVERSION OR SUBSTITUTION; COATING BY VACUUM EVAPORATION, BY SPUTTERING, BY ION IMPLANTATION OR BY CHEMICAL VAPOUR DEPOSITION, IN GENERAL (making metal-coated products by extrusion B21C23/22; covering with metal by connecting pre-existing layers to articles, see the relevant places, e.g. B21D39/00, B23K; metallising of glass C03C; metallising mortars, concrete, artificial stone, ceramics or natural stone C04B41/00; enamelling of, or applying a vitreous layer to, metals C23D; treating metal surfaces or coating of metals by electrolysis or electrophoresis C25D; single-crystal film growth C30B; by metallising textiles D06M11/83; decorating textiles by locally metallising D06Q1/04) - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Methods and systems for controlling concentration profiles of deposited films using machine learning are provided. Data associated with a target concentration profile for a film to be deposited on a surface of a substrate during a deposition process for the substrate is provided as input to a trained machine learning model. One or more outputs of the trained machine learning model are obtained. Process recipe data identifying one or more sets of deposition process settings is determined from the one or more outputs. For each set of deposition process setting, an indication of a level of confidence that a respective set of deposition process settings corresponds to the target concentration profile for the film to be deposited on the substrate is also determined. In response to an identification of the respective set of deposition process settings with a level of confidence that satisfies a level of confidence criterion, one or more operations of the deposition process are performed in accordance with the respective set of deposition process settings. ## Claims ### Claim 1 A method comprising: providing, as input to a trained machine learning model, data associated with a target concentration profile for a film to be deposited on a surface of a substrate during a deposition process for the substrate at a process chamber of a manufacturing system; obtaining one or more outputs of the trained machine learning model; determining, from the one or more outputs, process recipe data identifying one or more sets of deposition process settings and, for each set of deposition process settings, an indication of a level of confidence that a respective set of deposition process settings corresponds to the target concentration profile for the film to be deposited on the substrate; and responsive to identifying the respective set of deposition process settings with a level of confidence that satisfies a level of confidence criterion, performing one or more operations of the deposition process in accordance with the respective set of deposition process settings. ### Claim 2 (depends on 1) The method of claim 1, further comprising: receiving an indication of a target thickness for the film to be deposited on the surface of the substrate, an indication of a target initial concentration for a particular material of the film and an indication of a target final concentration for the particular material of the film; and determining the target concentration profile for the film based on the target thickness, the target initial concentration, and the target final concentration. ### Claim 3 (depends on 1) The method of claim 1, further comprising: provide, as an additional input to the trained machine learning model, a set of one or more process constraints associated with the deposition process. ### Claim 4 (depends on 1) The method of claim 1, wherein each set of deposition process settings is associated with a concentration profile for the film deposited on the surface of the substrate, and wherein the respective set of deposition process settings corresponds to the target concentration responsive to a determination that a difference between the concentration profile associated with the respective set of deposition process settings and the target concentration profile is below a threshold difference value. ### Claim 5 (depends on 1) The method of claim 1, wherein the deposition process for the substrate is associated with an initial set of deposition process settings, and wherein performing one or more operations of the deposition process in accordance with the respective set of deposition process settings comprises modifying one or more of the initial set of deposition process settings to correspond to one or more of the respective set of deposition process settings. ### Claim 6 (depends on 5) The method of claim 5, further comprising: transmitting, to a client device connected to the manufacturing system, a request to modify the one or more of the initial set of deposition process settings to correspond to the one or more of the respective set of deposition process settings; and receiving, from the client device, an instruction to modify the one or more of the initial set of deposition process settings to correspond to the one or more of the respective set of deposition settings, wherein the one or more of the initial set of deposition process settings are updated in accordance with the received instruction. ### Claim 7 (depends on 1) The method of claim 1, wherein the respective set of deposition process settings comprises at least one of: a temperature setting for the process chamber, a pressure setting for the process chamber, or a flow rate setting for a precursor for one or more materials of the film to be deposited on the surface of the substrate. ### Claim 8 (depends on 7) The method of claim 7, wherein the precursor for the one or more materials comprises at least one of a silicon-containing precursor or a boron-containing precursor. ### Claim 9 (depends on 1) The method of claim 1, wherein the level of confidence of the respective set of deposition process settings satisfies the level of confidence criterion responsive to a determination that the level of confidence exceeds a threshold level of confidence value. ### Claim 10 A system comprising: a memory; and a processing device coupled to the memory, wherein the processing device is to perform operations for training a machine learning model to predict one or more deposition settings for a deposition process to be performed for a current substrate at a manufacturing system, the operations comprising: generating first training data for the machine learning model, wherein the first training data comprises historical data associated with one or more prior deposition settings for a prior deposition process previously performed for a prior substrate at the manufacturing system, wherein the prior deposition process comprises depositing a prior film on a surface of a prior substrate; generating second training data for the machine learning model, wherein the second training data is associated with a historical concentration profile for the prior film deposited on the surface of the prior substrate; and providing the first training data and the second training data to train the machine learning model to predict, for the deposition process to be performed for the current substrate, which set of deposition settings for the deposition process corresponds to a target concentration profile for a film to be deposited on a surface of a current substrate. ### Claim 11 (depends on 10) The system of claim 10, wherein the one or more prior deposition settings for the prior deposition process comprise at least one of a prior temperature setting for the prior deposition process, a prior pressure setting for the prior deposition process, or a prior flow rate setting for a precursors for one or more materials of the prior film deposited on the surface of the prior substrate. ### Claim 12 (depends on 11) The system of claim 11, wherein the precursor for the one or more materials comprises at least one of a silicon-containing precursor or a boron-containing precursor. ### Claim 13 (depends on 10) The system of claim 10, wherein the historical concentration profile for the prior film corresponds to a historical metrology measurement value associated with the prior film and a historical concentration associated with the prior film. ### Claim 14 (depends on 10) The system of claim 10, wherein the deposition process for the current substrate and the prior deposition process for the prior substrate are each performed at a particular process chamber of the manufacturing system. ### Claim 15 (depends on 10) The system of claim 10, wherein the deposition process for the current substrate is performed at a first process chamber of the manufacturing system and the prior deposition process for the current substrate is performed at a second process chamber of the manufacturing system. ### Claim 16 A non-transitory computer readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to: provide, as input to a trained machine learning model, data associated with a target concentration profile for a film to be deposited on a surface of a substrate during a deposition process for the substrate at a process chamber of a manufacturing system; obtain one or more outputs of the trained machine learning model; determine, from the one or more outputs, process recipe data identifying one or more sets of deposition process settings and, for each set of deposition process settings, an indication of a level of confidence that a respective set of deposition process settings corresponds to the target concentration profile for the film to be deposited on the substrate; and responsive to identifying the respective set of deposition process settings with a level of confidence that satisfies a level of confidence criterion, perform one or more operations of the deposition process in accordance with the respective set of deposition process settings. ### Claim 17 (depends on 16) The non-transitory computer readable storage medium of claim 16, wherein the processing device is further to: receive an indication of a target thickness for the film to be deposited on the surface of the substrate, an indication of a target initial concentration for a particular material of the film and an indication of a target final concentration for the particular material of the film; and determine the target concentration profile for the film based on the target thickness, the target initial concentration, and the target final concentration. ### Claim 18 (depends on 16) The non-transitory computer readable storage medium of claim 16, wherein the processing device is further to: provide, as an additional input to the trained machine learning model, a set of one or more process constraints associated with the deposition process. ### Claim 19 (depends on 16) The non-transitory computer readable storage medium of claim 16, wherein each set of deposition process settings is associated with a concentration profile for the film deposited on the surface of the substrate, and wherein the respective set of deposition process settings corresponds to the target concentration responsive to a determination that a difference between the concentration profile associated with the respective set of deposition process settings and the target concentration profile is below a threshold difference value. ### Claim 20 (depends on 16) The non-transitory computer readable storage medium of claim 16, wherein the deposition process for the substrate is associated with an initial set of deposition process settings, and wherein to perform one or more operations of the deposition process in accordance with the respective set of deposition process settings, the processing device is to modify one or more of the initial set of deposition process settings to correspond to one or more of the respective set of deposition process settings.