Accelerating atomic structure search with cluster regularization

We present a method for accelerating the global structure optimization of atomic compounds. The method is demonstrated to speed up the finding of the anatase TiO2(001)-(1 × 4) surface reconstruction within a density functional tight-binding theory framework using an evolutionary algorithm. As a key...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Journal of chemical physics 2018-06, Vol.148 (24), p.241734-241734
Hauptverfasser: Sørensen, K. H., Jørgensen, M. S., Bruix, A., Hammer, B.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 241734
container_issue 24
container_start_page 241734
container_title The Journal of chemical physics
container_volume 148
creator Sørensen, K. H.
Jørgensen, M. S.
Bruix, A.
Hammer, B.
description We present a method for accelerating the global structure optimization of atomic compounds. The method is demonstrated to speed up the finding of the anatase TiO2(001)-(1 × 4) surface reconstruction within a density functional tight-binding theory framework using an evolutionary algorithm. As a key element of the method, we use unsupervised machine learning techniques to categorize atoms present in a diverse set of partially disordered surface structures into clusters of atoms having similar local atomic environments. Analysis of more than 1000 different structures shows that the total energy of the structures correlates with the summed distances of the atomic environments to their respective cluster centers in feature space, where the sum runs over all atoms in each structure. Our method is formulated as a gradient based minimization of this summed cluster distance for a given structure and alternates with a standard gradient based energy minimization. While the latter minimization ensures local relaxation within a given energy basin, the former enables escapes from meta-stable basins and hence increases the overall performance of the global optimization.
doi_str_mv 10.1063/1.5023671
format Article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmed_primary_29960341</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2063727478</sourcerecordid><originalsourceid>FETCH-LOGICAL-c383t-93c30c99963904383fa4c7e65daa08ae14f927dbea72baf97658ceaebb50426a3</originalsourceid><addsrcrecordid>eNp90F1LwzAUBuAgipvTC_-AFLxRofMkaZPmzjH8AsEbvQ5pmm4d7TrzoeivN7qpIOhV4PCcN4cXoUMMYwyMnuNxDoQyjrfQEEMhUs4EbKMhAMGpYMAGaM-5BQBgTrJdNCAiTmmGh-hiorVpjVW-Wc4S5fuu0YnzNmgfrEmcUVbPk5fGzxPdBueNTayZhVbZ5i3u9Mt9tFOr1pmDzTtCj1eXD9Ob9O7--nY6uUs1LahPBdUUtIj_UgFZHNUq09ywvFIKCmVwVgvCq9IoTkpVC87yQhtlyjKHjDBFR-hknbuy_VMwzsuucfH0Vi1NH5wksQhOeMaLSI9_0UUf7DJeF1VRsILlOY3qdK207Z2zppYr23TKvkoM8qNWieWm1miPNomh7Ez1Lb96jOBsDZxu_Gcv_6b9iZ97-wPlqqrpO3G1jZk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2088686553</pqid></control><display><type>article</type><title>Accelerating atomic structure search with cluster regularization</title><source>AIP Journals Complete</source><source>Alma/SFX Local Collection</source><creator>Sørensen, K. H. ; Jørgensen, M. S. ; Bruix, A. ; Hammer, B.</creator><creatorcontrib>Sørensen, K. H. ; Jørgensen, M. S. ; Bruix, A. ; Hammer, B.</creatorcontrib><description>We present a method for accelerating the global structure optimization of atomic compounds. The method is demonstrated to speed up the finding of the anatase TiO2(001)-(1 × 4) surface reconstruction within a density functional tight-binding theory framework using an evolutionary algorithm. As a key element of the method, we use unsupervised machine learning techniques to categorize atoms present in a diverse set of partially disordered surface structures into clusters of atoms having similar local atomic environments. Analysis of more than 1000 different structures shows that the total energy of the structures correlates with the summed distances of the atomic environments to their respective cluster centers in feature space, where the sum runs over all atoms in each structure. Our method is formulated as a gradient based minimization of this summed cluster distance for a given structure and alternates with a standard gradient based energy minimization. While the latter minimization ensures local relaxation within a given energy basin, the former enables escapes from meta-stable basins and hence increases the overall performance of the global optimization.</description><identifier>ISSN: 0021-9606</identifier><identifier>EISSN: 1089-7690</identifier><identifier>DOI: 10.1063/1.5023671</identifier><identifier>PMID: 29960341</identifier><identifier>CODEN: JCPSA6</identifier><language>eng</language><publisher>United States: American Institute of Physics</publisher><subject>Anatase ; Atomic structure ; Clusters ; Energy conservation ; Evolutionary algorithms ; Global optimization ; Machine learning ; Regularization ; Titanium dioxide</subject><ispartof>The Journal of chemical physics, 2018-06, Vol.148 (24), p.241734-241734</ispartof><rights>Author(s)</rights><rights>2018 Author(s). Published by AIP Publishing.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c383t-93c30c99963904383fa4c7e65daa08ae14f927dbea72baf97658ceaebb50426a3</citedby><cites>FETCH-LOGICAL-c383t-93c30c99963904383fa4c7e65daa08ae14f927dbea72baf97658ceaebb50426a3</cites><orcidid>0000-0001-7248-3185 ; 0000-0002-7849-6347 ; 0000-0003-0092-4708 ; 0000000172483185 ; 0000000300924708 ; 0000000278496347</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://pubs.aip.org/jcp/article-lookup/doi/10.1063/1.5023671$$EHTML$$P50$$Gscitation$$H</linktohtml><link.rule.ids>314,777,781,791,4498,27905,27906,76133</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/29960341$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Sørensen, K. H.</creatorcontrib><creatorcontrib>Jørgensen, M. S.</creatorcontrib><creatorcontrib>Bruix, A.</creatorcontrib><creatorcontrib>Hammer, B.</creatorcontrib><title>Accelerating atomic structure search with cluster regularization</title><title>The Journal of chemical physics</title><addtitle>J Chem Phys</addtitle><description>We present a method for accelerating the global structure optimization of atomic compounds. The method is demonstrated to speed up the finding of the anatase TiO2(001)-(1 × 4) surface reconstruction within a density functional tight-binding theory framework using an evolutionary algorithm. As a key element of the method, we use unsupervised machine learning techniques to categorize atoms present in a diverse set of partially disordered surface structures into clusters of atoms having similar local atomic environments. Analysis of more than 1000 different structures shows that the total energy of the structures correlates with the summed distances of the atomic environments to their respective cluster centers in feature space, where the sum runs over all atoms in each structure. Our method is formulated as a gradient based minimization of this summed cluster distance for a given structure and alternates with a standard gradient based energy minimization. While the latter minimization ensures local relaxation within a given energy basin, the former enables escapes from meta-stable basins and hence increases the overall performance of the global optimization.</description><subject>Anatase</subject><subject>Atomic structure</subject><subject>Clusters</subject><subject>Energy conservation</subject><subject>Evolutionary algorithms</subject><subject>Global optimization</subject><subject>Machine learning</subject><subject>Regularization</subject><subject>Titanium dioxide</subject><issn>0021-9606</issn><issn>1089-7690</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><recordid>eNp90F1LwzAUBuAgipvTC_-AFLxRofMkaZPmzjH8AsEbvQ5pmm4d7TrzoeivN7qpIOhV4PCcN4cXoUMMYwyMnuNxDoQyjrfQEEMhUs4EbKMhAMGpYMAGaM-5BQBgTrJdNCAiTmmGh-hiorVpjVW-Wc4S5fuu0YnzNmgfrEmcUVbPk5fGzxPdBueNTayZhVbZ5i3u9Mt9tFOr1pmDzTtCj1eXD9Ob9O7--nY6uUs1LahPBdUUtIj_UgFZHNUq09ywvFIKCmVwVgvCq9IoTkpVC87yQhtlyjKHjDBFR-hknbuy_VMwzsuucfH0Vi1NH5wksQhOeMaLSI9_0UUf7DJeF1VRsILlOY3qdK207Z2zppYr23TKvkoM8qNWieWm1miPNomh7Ez1Lb96jOBsDZxu_Gcv_6b9iZ97-wPlqqrpO3G1jZk</recordid><startdate>20180628</startdate><enddate>20180628</enddate><creator>Sørensen, K. H.</creator><creator>Jørgensen, M. S.</creator><creator>Bruix, A.</creator><creator>Hammer, B.</creator><general>American Institute of Physics</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-7248-3185</orcidid><orcidid>https://orcid.org/0000-0002-7849-6347</orcidid><orcidid>https://orcid.org/0000-0003-0092-4708</orcidid><orcidid>https://orcid.org/0000000172483185</orcidid><orcidid>https://orcid.org/0000000300924708</orcidid><orcidid>https://orcid.org/0000000278496347</orcidid></search><sort><creationdate>20180628</creationdate><title>Accelerating atomic structure search with cluster regularization</title><author>Sørensen, K. H. ; Jørgensen, M. S. ; Bruix, A. ; Hammer, B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c383t-93c30c99963904383fa4c7e65daa08ae14f927dbea72baf97658ceaebb50426a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Anatase</topic><topic>Atomic structure</topic><topic>Clusters</topic><topic>Energy conservation</topic><topic>Evolutionary algorithms</topic><topic>Global optimization</topic><topic>Machine learning</topic><topic>Regularization</topic><topic>Titanium dioxide</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Sørensen, K. H.</creatorcontrib><creatorcontrib>Jørgensen, M. S.</creatorcontrib><creatorcontrib>Bruix, A.</creatorcontrib><creatorcontrib>Hammer, B.</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>MEDLINE - Academic</collection><jtitle>The Journal of chemical physics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sørensen, K. H.</au><au>Jørgensen, M. S.</au><au>Bruix, A.</au><au>Hammer, B.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Accelerating atomic structure search with cluster regularization</atitle><jtitle>The Journal of chemical physics</jtitle><addtitle>J Chem Phys</addtitle><date>2018-06-28</date><risdate>2018</risdate><volume>148</volume><issue>24</issue><spage>241734</spage><epage>241734</epage><pages>241734-241734</pages><issn>0021-9606</issn><eissn>1089-7690</eissn><coden>JCPSA6</coden><abstract>We present a method for accelerating the global structure optimization of atomic compounds. The method is demonstrated to speed up the finding of the anatase TiO2(001)-(1 × 4) surface reconstruction within a density functional tight-binding theory framework using an evolutionary algorithm. As a key element of the method, we use unsupervised machine learning techniques to categorize atoms present in a diverse set of partially disordered surface structures into clusters of atoms having similar local atomic environments. Analysis of more than 1000 different structures shows that the total energy of the structures correlates with the summed distances of the atomic environments to their respective cluster centers in feature space, where the sum runs over all atoms in each structure. Our method is formulated as a gradient based minimization of this summed cluster distance for a given structure and alternates with a standard gradient based energy minimization. While the latter minimization ensures local relaxation within a given energy basin, the former enables escapes from meta-stable basins and hence increases the overall performance of the global optimization.</abstract><cop>United States</cop><pub>American Institute of Physics</pub><pmid>29960341</pmid><doi>10.1063/1.5023671</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0001-7248-3185</orcidid><orcidid>https://orcid.org/0000-0002-7849-6347</orcidid><orcidid>https://orcid.org/0000-0003-0092-4708</orcidid><orcidid>https://orcid.org/0000000172483185</orcidid><orcidid>https://orcid.org/0000000300924708</orcidid><orcidid>https://orcid.org/0000000278496347</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0021-9606
ispartof The Journal of chemical physics, 2018-06, Vol.148 (24), p.241734-241734
issn 0021-9606
1089-7690
language eng
recordid cdi_pubmed_primary_29960341
source AIP Journals Complete; Alma/SFX Local Collection
subjects Anatase
Atomic structure
Clusters
Energy conservation
Evolutionary algorithms
Global optimization
Machine learning
Regularization
Titanium dioxide
title Accelerating atomic structure search with cluster regularization
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T13%3A10%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Accelerating%20atomic%20structure%20search%20with%20cluster%20regularization&rft.jtitle=The%20Journal%20of%20chemical%20physics&rft.au=S%C3%B8rensen,%20K.%20H.&rft.date=2018-06-28&rft.volume=148&rft.issue=24&rft.spage=241734&rft.epage=241734&rft.pages=241734-241734&rft.issn=0021-9606&rft.eissn=1089-7690&rft.coden=JCPSA6&rft_id=info:doi/10.1063/1.5023671&rft_dat=%3Cproquest_pubme%3E2063727478%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2088686553&rft_id=info:pmid/29960341&rfr_iscdi=true