Prediction of Transition-State Energies of Hydrodeoxygenation Reactions on Transition-Metal Surfaces Based on Machine Learning

Computational catalyst discovery involves identification of a meaningful model and suitable descriptors that determine the catalyst properties. We study the impact of combining various descriptors (e.g., reaction energies, metal descriptors, and bond counts) for modeling transition-state energies (T...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of physical chemistry. C 2019-12, Vol.123 (49), p.29804-29810
Hauptverfasser: Abdelfatah, Kareem, Yang, Wenqiang, Vijay Solomon, Rajadurai, Rajbanshi, Biplab, Chowdhury, Asif, Zare, Mehdi, Kundu, Subrata Kumar, Yonge, Adam, Heyden, Andreas, Terejanu, Gabriel
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 29810
container_issue 49
container_start_page 29804
container_title Journal of physical chemistry. C
container_volume 123
creator Abdelfatah, Kareem
Yang, Wenqiang
Vijay Solomon, Rajadurai
Rajbanshi, Biplab
Chowdhury, Asif
Zare, Mehdi
Kundu, Subrata Kumar
Yonge, Adam
Heyden, Andreas
Terejanu, Gabriel
description Computational catalyst discovery involves identification of a meaningful model and suitable descriptors that determine the catalyst properties. We study the impact of combining various descriptors (e.g., reaction energies, metal descriptors, and bond counts) for modeling transition-state energies (TS) based on a database of adsorption and TS energies across transition-metal surfaces for the decarboxylation and decarbonylation of propionic acid, a chemistry characteristic for biomass conversion. Results of different machine learning models for more than 1572 descriptor combinations suggest that there is no statistically significant difference between linear and nonlinear models when using the right combination of reactant energies, metal descriptors, and bond counts. However, linear models are inferior when not including bond count and metal descriptors. Furthermore, when there are missing data for reaction steps on all metals, conventional linear scaling is inferior to linear and nonlinear models with proper choice of descriptors that are surprisingly robust.
doi_str_mv 10.1021/acs.jpcc.9b10507
format Article
fullrecord <record><control><sourceid>acs_osti_</sourceid><recordid>TN_cdi_osti_scitechconnect_1656918</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>a425535935</sourcerecordid><originalsourceid>FETCH-LOGICAL-a386t-b20a337769c2d6f41293ec095c1155c3016a3a354e9e8eceef8f34b20f08b7743</originalsourceid><addsrcrecordid>eNp1kM1PAjEQxRujiYjePW48u9hut_txVKJiAtEInpuhO4USbEm7JHLxb7cLxHjxNDN57zfJe4RcMzpgNGN3oMJgtVFqUM8ZFbQ8IT1W8ywtcyFOf_e8PCcXIawoFZwy3iPfbx4bo1rjbOJ0MvNgg-mudNpCi8mjRb8wGDpxtGu8a9B97RZoYY-8I-zZqNu_8ARbWCfTrdegIvwAAZvOMgG1NBaTMYK3xi4uyZmGdcCr4-yTj6fH2XCUjl-fX4b34xR4VbTpPKPAeVkWtcqaQucsqzkqWgvFmBAqRimAAxc51lihQtSV5nmkNK3mZZnzPrk5_HWhNTIo06JaKmctqlayQhQ1q6KJHkzKuxA8arnx5hP8TjIqu5JlLFl2JctjyRG5PSB7xW29jSn-t_8A4AqCMw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Prediction of Transition-State Energies of Hydrodeoxygenation Reactions on Transition-Metal Surfaces Based on Machine Learning</title><source>American Chemical Society Journals</source><creator>Abdelfatah, Kareem ; Yang, Wenqiang ; Vijay Solomon, Rajadurai ; Rajbanshi, Biplab ; Chowdhury, Asif ; Zare, Mehdi ; Kundu, Subrata Kumar ; Yonge, Adam ; Heyden, Andreas ; Terejanu, Gabriel</creator><creatorcontrib>Abdelfatah, Kareem ; Yang, Wenqiang ; Vijay Solomon, Rajadurai ; Rajbanshi, Biplab ; Chowdhury, Asif ; Zare, Mehdi ; Kundu, Subrata Kumar ; Yonge, Adam ; Heyden, Andreas ; Terejanu, Gabriel ; Univ. of South Carolina, Columbia, SC (United States)</creatorcontrib><description>Computational catalyst discovery involves identification of a meaningful model and suitable descriptors that determine the catalyst properties. We study the impact of combining various descriptors (e.g., reaction energies, metal descriptors, and bond counts) for modeling transition-state energies (TS) based on a database of adsorption and TS energies across transition-metal surfaces for the decarboxylation and decarbonylation of propionic acid, a chemistry characteristic for biomass conversion. Results of different machine learning models for more than 1572 descriptor combinations suggest that there is no statistically significant difference between linear and nonlinear models when using the right combination of reactant energies, metal descriptors, and bond counts. However, linear models are inferior when not including bond count and metal descriptors. Furthermore, when there are missing data for reaction steps on all metals, conventional linear scaling is inferior to linear and nonlinear models with proper choice of descriptors that are surprisingly robust.</description><identifier>ISSN: 1932-7447</identifier><identifier>EISSN: 1932-7455</identifier><identifier>DOI: 10.1021/acs.jpcc.9b10507</identifier><language>eng</language><publisher>United States: American Chemical Society</publisher><subject>Adsorption ; Chemical reactions ; Energy ; Free energy ; INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY ; Metals</subject><ispartof>Journal of physical chemistry. C, 2019-12, Vol.123 (49), p.29804-29810</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a386t-b20a337769c2d6f41293ec095c1155c3016a3a354e9e8eceef8f34b20f08b7743</citedby><cites>FETCH-LOGICAL-a386t-b20a337769c2d6f41293ec095c1155c3016a3a354e9e8eceef8f34b20f08b7743</cites><orcidid>0000-0001-8556-462X ; 0000-0002-4939-7489 ; 000000018556462X ; 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.jpcc.9b10507$$EPDF$$P50$$Gacs$$H</linktopdf><linktohtml>$$Uhttps://pubs.acs.org/doi/10.1021/acs.jpcc.9b10507$$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.osti.gov/servlets/purl/1656918$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Abdelfatah, Kareem</creatorcontrib><creatorcontrib>Yang, Wenqiang</creatorcontrib><creatorcontrib>Vijay Solomon, Rajadurai</creatorcontrib><creatorcontrib>Rajbanshi, Biplab</creatorcontrib><creatorcontrib>Chowdhury, Asif</creatorcontrib><creatorcontrib>Zare, Mehdi</creatorcontrib><creatorcontrib>Kundu, Subrata Kumar</creatorcontrib><creatorcontrib>Yonge, Adam</creatorcontrib><creatorcontrib>Heyden, Andreas</creatorcontrib><creatorcontrib>Terejanu, Gabriel</creatorcontrib><creatorcontrib>Univ. of South Carolina, Columbia, SC (United States)</creatorcontrib><title>Prediction of Transition-State Energies of Hydrodeoxygenation Reactions on Transition-Metal Surfaces Based on Machine Learning</title><title>Journal of physical chemistry. C</title><addtitle>J. Phys. Chem. C</addtitle><description>Computational catalyst discovery involves identification of a meaningful model and suitable descriptors that determine the catalyst properties. We study the impact of combining various descriptors (e.g., reaction energies, metal descriptors, and bond counts) for modeling transition-state energies (TS) based on a database of adsorption and TS energies across transition-metal surfaces for the decarboxylation and decarbonylation of propionic acid, a chemistry characteristic for biomass conversion. Results of different machine learning models for more than 1572 descriptor combinations suggest that there is no statistically significant difference between linear and nonlinear models when using the right combination of reactant energies, metal descriptors, and bond counts. However, linear models are inferior when not including bond count and metal descriptors. Furthermore, when there are missing data for reaction steps on all metals, conventional linear scaling is inferior to linear and nonlinear models with proper choice of descriptors that are surprisingly robust.</description><subject>Adsorption</subject><subject>Chemical reactions</subject><subject>Energy</subject><subject>Free energy</subject><subject>INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY</subject><subject>Metals</subject><issn>1932-7447</issn><issn>1932-7455</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNp1kM1PAjEQxRujiYjePW48u9hut_txVKJiAtEInpuhO4USbEm7JHLxb7cLxHjxNDN57zfJe4RcMzpgNGN3oMJgtVFqUM8ZFbQ8IT1W8ywtcyFOf_e8PCcXIawoFZwy3iPfbx4bo1rjbOJ0MvNgg-mudNpCi8mjRb8wGDpxtGu8a9B97RZoYY-8I-zZqNu_8ARbWCfTrdegIvwAAZvOMgG1NBaTMYK3xi4uyZmGdcCr4-yTj6fH2XCUjl-fX4b34xR4VbTpPKPAeVkWtcqaQucsqzkqWgvFmBAqRimAAxc51lihQtSV5nmkNK3mZZnzPrk5_HWhNTIo06JaKmctqlayQhQ1q6KJHkzKuxA8arnx5hP8TjIqu5JlLFl2JctjyRG5PSB7xW29jSn-t_8A4AqCMw</recordid><startdate>20191212</startdate><enddate>20191212</enddate><creator>Abdelfatah, Kareem</creator><creator>Yang, Wenqiang</creator><creator>Vijay Solomon, Rajadurai</creator><creator>Rajbanshi, Biplab</creator><creator>Chowdhury, Asif</creator><creator>Zare, Mehdi</creator><creator>Kundu, Subrata Kumar</creator><creator>Yonge, Adam</creator><creator>Heyden, Andreas</creator><creator>Terejanu, Gabriel</creator><general>American Chemical Society</general><scope>AAYXX</scope><scope>CITATION</scope><scope>OIOZB</scope><scope>OTOTI</scope><orcidid>https://orcid.org/0000-0001-8556-462X</orcidid><orcidid>https://orcid.org/0000-0002-4939-7489</orcidid><orcidid>https://orcid.org/000000018556462X</orcidid><orcidid>https://orcid.org/0000000249397489</orcidid></search><sort><creationdate>20191212</creationdate><title>Prediction of Transition-State Energies of Hydrodeoxygenation Reactions on Transition-Metal Surfaces Based on Machine Learning</title><author>Abdelfatah, Kareem ; Yang, Wenqiang ; Vijay Solomon, Rajadurai ; Rajbanshi, Biplab ; Chowdhury, Asif ; Zare, Mehdi ; Kundu, Subrata Kumar ; Yonge, Adam ; Heyden, Andreas ; Terejanu, Gabriel</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a386t-b20a337769c2d6f41293ec095c1155c3016a3a354e9e8eceef8f34b20f08b7743</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Adsorption</topic><topic>Chemical reactions</topic><topic>Energy</topic><topic>Free energy</topic><topic>INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY</topic><topic>Metals</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Abdelfatah, Kareem</creatorcontrib><creatorcontrib>Yang, Wenqiang</creatorcontrib><creatorcontrib>Vijay Solomon, Rajadurai</creatorcontrib><creatorcontrib>Rajbanshi, Biplab</creatorcontrib><creatorcontrib>Chowdhury, Asif</creatorcontrib><creatorcontrib>Zare, Mehdi</creatorcontrib><creatorcontrib>Kundu, Subrata Kumar</creatorcontrib><creatorcontrib>Yonge, Adam</creatorcontrib><creatorcontrib>Heyden, Andreas</creatorcontrib><creatorcontrib>Terejanu, Gabriel</creatorcontrib><creatorcontrib>Univ. of South Carolina, Columbia, SC (United States)</creatorcontrib><collection>CrossRef</collection><collection>OSTI.GOV - Hybrid</collection><collection>OSTI.GOV</collection><jtitle>Journal of physical chemistry. C</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Abdelfatah, Kareem</au><au>Yang, Wenqiang</au><au>Vijay Solomon, Rajadurai</au><au>Rajbanshi, Biplab</au><au>Chowdhury, Asif</au><au>Zare, Mehdi</au><au>Kundu, Subrata Kumar</au><au>Yonge, Adam</au><au>Heyden, Andreas</au><au>Terejanu, Gabriel</au><aucorp>Univ. of South Carolina, Columbia, SC (United States)</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Prediction of Transition-State Energies of Hydrodeoxygenation Reactions on Transition-Metal Surfaces Based on Machine Learning</atitle><jtitle>Journal of physical chemistry. C</jtitle><addtitle>J. Phys. Chem. C</addtitle><date>2019-12-12</date><risdate>2019</risdate><volume>123</volume><issue>49</issue><spage>29804</spage><epage>29810</epage><pages>29804-29810</pages><issn>1932-7447</issn><eissn>1932-7455</eissn><abstract>Computational catalyst discovery involves identification of a meaningful model and suitable descriptors that determine the catalyst properties. We study the impact of combining various descriptors (e.g., reaction energies, metal descriptors, and bond counts) for modeling transition-state energies (TS) based on a database of adsorption and TS energies across transition-metal surfaces for the decarboxylation and decarbonylation of propionic acid, a chemistry characteristic for biomass conversion. Results of different machine learning models for more than 1572 descriptor combinations suggest that there is no statistically significant difference between linear and nonlinear models when using the right combination of reactant energies, metal descriptors, and bond counts. However, linear models are inferior when not including bond count and metal descriptors. Furthermore, when there are missing data for reaction steps on all metals, conventional linear scaling is inferior to linear and nonlinear models with proper choice of descriptors that are surprisingly robust.</abstract><cop>United States</cop><pub>American Chemical Society</pub><doi>10.1021/acs.jpcc.9b10507</doi><tpages>7</tpages><orcidid>https://orcid.org/0000-0001-8556-462X</orcidid><orcidid>https://orcid.org/0000-0002-4939-7489</orcidid><orcidid>https://orcid.org/000000018556462X</orcidid><orcidid>https://orcid.org/0000000249397489</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1932-7447
ispartof Journal of physical chemistry. C, 2019-12, Vol.123 (49), p.29804-29810
issn 1932-7447
1932-7455
language eng
recordid cdi_osti_scitechconnect_1656918
source American Chemical Society Journals
subjects Adsorption
Chemical reactions
Energy
Free energy
INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
Metals
title Prediction of Transition-State Energies of Hydrodeoxygenation Reactions on Transition-Metal Surfaces Based on Machine Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T04%3A47%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-acs_osti_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Prediction%20of%20Transition-State%20Energies%20of%20Hydrodeoxygenation%20Reactions%20on%20Transition-Metal%20Surfaces%20Based%20on%20Machine%20Learning&rft.jtitle=Journal%20of%20physical%20chemistry.%20C&rft.au=Abdelfatah,%20Kareem&rft.aucorp=Univ.%20of%20South%20Carolina,%20Columbia,%20SC%20(United%20States)&rft.date=2019-12-12&rft.volume=123&rft.issue=49&rft.spage=29804&rft.epage=29810&rft.pages=29804-29810&rft.issn=1932-7447&rft.eissn=1932-7455&rft_id=info:doi/10.1021/acs.jpcc.9b10507&rft_dat=%3Cacs_osti_%3Ea425535935%3C/acs_osti_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true