A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications
Computational catalyst discovery involves the development of microkinetic reactor models based on estimated parameters determined from density functional theory (DFT). For complex surface chemistries, the number of reaction intermediates can be very large, and the cost of calculating the adsorption...
Gespeichert in:
Veröffentlicht in: | Journal of chemical theory and computation 2020-02, Vol.16 (2), p.1105-1114 |
---|---|
Hauptverfasser: | , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 1114 |
---|---|
container_issue | 2 |
container_start_page | 1105 |
container_title | Journal of chemical theory and computation |
container_volume | 16 |
creator | Chowdhury, Asif J Yang, Wenqiang Abdelfatah, Kareem E Zare, Mehdi Heyden, Andreas Terejanu, Gabriel A |
description | Computational catalyst discovery involves the development of microkinetic reactor models based on estimated parameters determined from density functional theory (DFT). For complex surface chemistries, the number of reaction intermediates can be very large, and the cost of calculating the adsorption energies by DFT for all surface intermediates even for one active site model can become prohibitive. In this paper, we have identified appropriate descriptors and machine learning models that can be used to predict a significant part of these adsorption energies given data on the rest of them. Moreover, our investigations also included the case when the species data used to train the predictive model are of different size relative to the species the model tries to predictthis is an extrapolation in the data space which is typically difficult with regular machine learning models. Due to the relative size of the available data sets, we have attempted to extrapolate from the larger species to the smaller ones in the current work. Here, we have developed a neural network based predictive model that combines an established additive atomic contribution based model with the concepts of a convolutional neural network that, when extrapolating, achieves a statistically significant improvement over the previous models. |
doi_str_mv | 10.1021/acs.jctc.9b00986 |
format | Article |
fullrecord | <record><control><sourceid>proquest_osti_</sourceid><recordid>TN_cdi_osti_scitechconnect_1656919</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2343516909</sourcerecordid><originalsourceid>FETCH-LOGICAL-a391t-8d76c15f7916936e1ad267d3a507662f28a9edf33ae27e9a9c8d4e8133934a173</originalsourceid><addsrcrecordid>eNp1kU9vEzEQxS0EoqVw54QsuHAgwX92vetjiFJAauEAnK2pd5Y4OOvF9gr6DfjYeJO0ByROMx793huPHiHPOVtyJvhbsGm5s9ku9Q1julUPyDmvK73QSqiH9z1vz8iTlHaMSVkJ-ZicSV4IVvFz8mdFryef3eiRXjqfMdJ3kLCjn3CK4EvJv0L8QVfjGAPYLc2B5i3Sze8cYQwesgsDDT1ddSnE8fDaDBi_O0y09NeYi8uXKfZgy6QPka6hjG6TS7Opd_ZgkZ6SRz34hM9O9YJ8u9x8XX9YXH1-_3G9ulqA1Dwv2q5Rltd9o7nSUiGHTqimk1CzRinRixY0dr2UgKJBDdq2XYUtl1LLCngjL8jLo29I2ZlkXUa7tWEY0GbDVa001wV6fYTK0T8nTNnsXbLoPQwYpmSErGRdPsBm9NU_6C5McSgnFKquWiEbNVPsSNkYUorYmzG6PcRbw5mZozQlSjNHaU5RFsmLk_F0s8fuXnCXXQHeHIGD9G7pf_3-AjSuqmc</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2354823769</pqid></control><display><type>article</type><title>A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications</title><source>American Chemical Society Journals</source><creator>Chowdhury, Asif J ; Yang, Wenqiang ; Abdelfatah, Kareem E ; Zare, Mehdi ; Heyden, Andreas ; Terejanu, Gabriel A</creator><creatorcontrib>Chowdhury, Asif J ; Yang, Wenqiang ; Abdelfatah, Kareem E ; Zare, Mehdi ; Heyden, Andreas ; Terejanu, Gabriel A ; Univ. of South Carolina, Columbia, SC (United States)</creatorcontrib><description>Computational catalyst discovery involves the development of microkinetic reactor models based on estimated parameters determined from density functional theory (DFT). For complex surface chemistries, the number of reaction intermediates can be very large, and the cost of calculating the adsorption energies by DFT for all surface intermediates even for one active site model can become prohibitive. In this paper, we have identified appropriate descriptors and machine learning models that can be used to predict a significant part of these adsorption energies given data on the rest of them. Moreover, our investigations also included the case when the species data used to train the predictive model are of different size relative to the species the model tries to predictthis is an extrapolation in the data space which is typically difficult with regular machine learning models. Due to the relative size of the available data sets, we have attempted to extrapolate from the larger species to the smaller ones in the current work. Here, we have developed a neural network based predictive model that combines an established additive atomic contribution based model with the concepts of a convolutional neural network that, when extrapolating, achieves a statistically significant improvement over the previous models.</description><identifier>ISSN: 1549-9618</identifier><identifier>EISSN: 1549-9626</identifier><identifier>DOI: 10.1021/acs.jctc.9b00986</identifier><identifier>PMID: 31962041</identifier><language>eng</language><publisher>United States: American Chemical Society</publisher><subject>Adsorption ; Artificial neural networks ; Catalysis ; Density functional theory ; Energy ; Extrapolation ; INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY ; Machine learning ; Metal surfaces ; Molecular modeling ; Molecules ; Neural networks ; Organic chemistry ; Parameter estimation ; Prediction models ; Surface chemistry</subject><ispartof>Journal of chemical theory and computation, 2020-02, Vol.16 (2), p.1105-1114</ispartof><rights>Copyright American Chemical Society Feb 11, 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a391t-8d76c15f7916936e1ad267d3a507662f28a9edf33ae27e9a9c8d4e8133934a173</citedby><cites>FETCH-LOGICAL-a391t-8d76c15f7916936e1ad267d3a507662f28a9edf33ae27e9a9c8d4e8133934a173</cites><orcidid>0000-0002-4939-7489 ; 0000000249397489</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://pubs.acs.org/doi/pdf/10.1021/acs.jctc.9b00986$$EPDF$$P50$$Gacs$$H</linktopdf><linktohtml>$$Uhttps://pubs.acs.org/doi/10.1021/acs.jctc.9b00986$$EHTML$$P50$$Gacs$$H</linktohtml><link.rule.ids>230,314,780,784,885,2765,27076,27924,27925,56738,56788</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/31962041$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink><backlink>$$Uhttps://www.osti.gov/servlets/purl/1656919$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Chowdhury, Asif J</creatorcontrib><creatorcontrib>Yang, Wenqiang</creatorcontrib><creatorcontrib>Abdelfatah, Kareem E</creatorcontrib><creatorcontrib>Zare, Mehdi</creatorcontrib><creatorcontrib>Heyden, Andreas</creatorcontrib><creatorcontrib>Terejanu, Gabriel A</creatorcontrib><creatorcontrib>Univ. of South Carolina, Columbia, SC (United States)</creatorcontrib><title>A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications</title><title>Journal of chemical theory and computation</title><addtitle>J. Chem. Theory Comput</addtitle><description>Computational catalyst discovery involves the development of microkinetic reactor models based on estimated parameters determined from density functional theory (DFT). For complex surface chemistries, the number of reaction intermediates can be very large, and the cost of calculating the adsorption energies by DFT for all surface intermediates even for one active site model can become prohibitive. In this paper, we have identified appropriate descriptors and machine learning models that can be used to predict a significant part of these adsorption energies given data on the rest of them. Moreover, our investigations also included the case when the species data used to train the predictive model are of different size relative to the species the model tries to predictthis is an extrapolation in the data space which is typically difficult with regular machine learning models. Due to the relative size of the available data sets, we have attempted to extrapolate from the larger species to the smaller ones in the current work. Here, we have developed a neural network based predictive model that combines an established additive atomic contribution based model with the concepts of a convolutional neural network that, when extrapolating, achieves a statistically significant improvement over the previous models.</description><subject>Adsorption</subject><subject>Artificial neural networks</subject><subject>Catalysis</subject><subject>Density functional theory</subject><subject>Energy</subject><subject>Extrapolation</subject><subject>INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY</subject><subject>Machine learning</subject><subject>Metal surfaces</subject><subject>Molecular modeling</subject><subject>Molecules</subject><subject>Neural networks</subject><subject>Organic chemistry</subject><subject>Parameter estimation</subject><subject>Prediction models</subject><subject>Surface chemistry</subject><issn>1549-9618</issn><issn>1549-9626</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNp1kU9vEzEQxS0EoqVw54QsuHAgwX92vetjiFJAauEAnK2pd5Y4OOvF9gr6DfjYeJO0ByROMx793huPHiHPOVtyJvhbsGm5s9ku9Q1julUPyDmvK73QSqiH9z1vz8iTlHaMSVkJ-ZicSV4IVvFz8mdFryef3eiRXjqfMdJ3kLCjn3CK4EvJv0L8QVfjGAPYLc2B5i3Sze8cYQwesgsDDT1ddSnE8fDaDBi_O0y09NeYi8uXKfZgy6QPka6hjG6TS7Opd_ZgkZ6SRz34hM9O9YJ8u9x8XX9YXH1-_3G9ulqA1Dwv2q5Rltd9o7nSUiGHTqimk1CzRinRixY0dr2UgKJBDdq2XYUtl1LLCngjL8jLo29I2ZlkXUa7tWEY0GbDVa001wV6fYTK0T8nTNnsXbLoPQwYpmSErGRdPsBm9NU_6C5McSgnFKquWiEbNVPsSNkYUorYmzG6PcRbw5mZozQlSjNHaU5RFsmLk_F0s8fuXnCXXQHeHIGD9G7pf_3-AjSuqmc</recordid><startdate>20200211</startdate><enddate>20200211</enddate><creator>Chowdhury, Asif J</creator><creator>Yang, Wenqiang</creator><creator>Abdelfatah, Kareem E</creator><creator>Zare, Mehdi</creator><creator>Heyden, Andreas</creator><creator>Terejanu, Gabriel A</creator><general>American Chemical Society</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SR</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><scope>OIOZB</scope><scope>OTOTI</scope><orcidid>https://orcid.org/0000-0002-4939-7489</orcidid><orcidid>https://orcid.org/0000000249397489</orcidid></search><sort><creationdate>20200211</creationdate><title>A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications</title><author>Chowdhury, Asif J ; Yang, Wenqiang ; Abdelfatah, Kareem E ; Zare, Mehdi ; Heyden, Andreas ; Terejanu, Gabriel A</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a391t-8d76c15f7916936e1ad267d3a507662f28a9edf33ae27e9a9c8d4e8133934a173</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Adsorption</topic><topic>Artificial neural networks</topic><topic>Catalysis</topic><topic>Density functional theory</topic><topic>Energy</topic><topic>Extrapolation</topic><topic>INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY</topic><topic>Machine learning</topic><topic>Metal surfaces</topic><topic>Molecular modeling</topic><topic>Molecules</topic><topic>Neural networks</topic><topic>Organic chemistry</topic><topic>Parameter estimation</topic><topic>Prediction models</topic><topic>Surface chemistry</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Chowdhury, Asif J</creatorcontrib><creatorcontrib>Yang, Wenqiang</creatorcontrib><creatorcontrib>Abdelfatah, Kareem E</creatorcontrib><creatorcontrib>Zare, Mehdi</creatorcontrib><creatorcontrib>Heyden, Andreas</creatorcontrib><creatorcontrib>Terejanu, Gabriel A</creatorcontrib><creatorcontrib>Univ. of South Carolina, Columbia, SC (United States)</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><collection>OSTI.GOV - Hybrid</collection><collection>OSTI.GOV</collection><jtitle>Journal of chemical theory and computation</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chowdhury, Asif J</au><au>Yang, Wenqiang</au><au>Abdelfatah, Kareem E</au><au>Zare, Mehdi</au><au>Heyden, Andreas</au><au>Terejanu, Gabriel A</au><aucorp>Univ. of South Carolina, Columbia, SC (United States)</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications</atitle><jtitle>Journal of chemical theory and computation</jtitle><addtitle>J. Chem. Theory Comput</addtitle><date>2020-02-11</date><risdate>2020</risdate><volume>16</volume><issue>2</issue><spage>1105</spage><epage>1114</epage><pages>1105-1114</pages><issn>1549-9618</issn><eissn>1549-9626</eissn><abstract>Computational catalyst discovery involves the development of microkinetic reactor models based on estimated parameters determined from density functional theory (DFT). For complex surface chemistries, the number of reaction intermediates can be very large, and the cost of calculating the adsorption energies by DFT for all surface intermediates even for one active site model can become prohibitive. In this paper, we have identified appropriate descriptors and machine learning models that can be used to predict a significant part of these adsorption energies given data on the rest of them. Moreover, our investigations also included the case when the species data used to train the predictive model are of different size relative to the species the model tries to predictthis is an extrapolation in the data space which is typically difficult with regular machine learning models. Due to the relative size of the available data sets, we have attempted to extrapolate from the larger species to the smaller ones in the current work. Here, we have developed a neural network based predictive model that combines an established additive atomic contribution based model with the concepts of a convolutional neural network that, when extrapolating, achieves a statistically significant improvement over the previous models.</abstract><cop>United States</cop><pub>American Chemical Society</pub><pmid>31962041</pmid><doi>10.1021/acs.jctc.9b00986</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0002-4939-7489</orcidid><orcidid>https://orcid.org/0000000249397489</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1549-9618 |
ispartof | Journal of chemical theory and computation, 2020-02, Vol.16 (2), p.1105-1114 |
issn | 1549-9618 1549-9626 |
language | eng |
recordid | cdi_osti_scitechconnect_1656919 |
source | American Chemical Society Journals |
subjects | Adsorption Artificial neural networks Catalysis Density functional theory Energy Extrapolation INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY Machine learning Metal surfaces Molecular modeling Molecules Neural networks Organic chemistry Parameter estimation Prediction models Surface chemistry |
title | A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T23%3A51%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_osti_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Multiple%20Filter%20Based%20Neural%20Network%20Approach%20to%20the%20Extrapolation%20of%20Adsorption%20Energies%20on%20Metal%20Surfaces%20for%20Catalysis%20Applications&rft.jtitle=Journal%20of%20chemical%20theory%20and%20computation&rft.au=Chowdhury,%20Asif%20J&rft.aucorp=Univ.%20of%20South%20Carolina,%20Columbia,%20SC%20(United%20States)&rft.date=2020-02-11&rft.volume=16&rft.issue=2&rft.spage=1105&rft.epage=1114&rft.pages=1105-1114&rft.issn=1549-9618&rft.eissn=1549-9626&rft_id=info:doi/10.1021/acs.jctc.9b00986&rft_dat=%3Cproquest_osti_%3E2343516909%3C/proquest_osti_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2354823769&rft_id=info:pmid/31962041&rfr_iscdi=true |