Unified representation of molecules and crystals for machine learning

Lade...
Vorschaubild
Dateien
Huo_2-19w1s7csvosh5.pdf
Huo_2-19w1s7csvosh5.pdfGröße: 780.17 KBDownloads: 265
Datum
2022
Autor:innen
Huo, Haoyan
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
ArXiv-ID
Internationale Patentnummer
Angaben zur Forschungsförderung
European Union (EU): 676580
Projekt
Open Access-Veröffentlichung
Open Access Gold
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Zeitschriftenartikel
Publikationsstatus
Published
Erschienen in
Machine Learning: Science and Technology. IOP Publishing. 2022, 3(4), 045017. eISSN 2632-2153. Available under: doi: 10.1088/2632-2153/aca005
Zusammenfassung

Accurate simulations of atomistic systems from first principles are limited by computational cost. In high-throughput settings, machine learning can reduce these costs significantly by accurately interpolating between reference calculations. For this, kernel learning approaches crucially require a representation that accommodates arbitrary atomistic systems. We introduce a many-body tensor representation that is invariant to translations, rotations, and nuclear permutations of same elements, unique, differentiable, can represent molecules and crystals, and is fast to compute. Empirical evidence for competitive energy and force prediction errors is presented for changes in molecular structure, crystal chemistry, and molecular dynamics using kernel regression and symmetric gradient-domain machine learning as models. Applicability is demonstrated for phase diagrams of Pt-group/transition-metal binary systems.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
many-body tensor representation, machine-learning potential, atomistic simulations
Konferenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690HUO, Haoyan, Matthias RUPP, 2022. Unified representation of molecules and crystals for machine learning. In: Machine Learning: Science and Technology. IOP Publishing. 2022, 3(4), 045017. eISSN 2632-2153. Available under: doi: 10.1088/2632-2153/aca005
BibTex
@article{Huo2022Unifi-59261,
  year={2022},
  doi={10.1088/2632-2153/aca005},
  title={Unified representation of molecules and crystals for machine learning},
  number={4},
  volume={3},
  journal={Machine Learning: Science and Technology},
  author={Huo, Haoyan and Rupp, Matthias},
  note={Article Number: 045017}
}
RDF
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/59261">
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Rupp, Matthias</dc:creator>
    <dc:rights>terms-of-use</dc:rights>
    <dc:creator>Huo, Haoyan</dc:creator>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/59261/3/Huo_2-19w1s7csvosh5.pdf"/>
    <dcterms:issued>2022</dcterms:issued>
    <dcterms:title>Unified representation of molecules and crystals for machine learning</dcterms:title>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/59261/3/Huo_2-19w1s7csvosh5.pdf"/>
    <dc:contributor>Rupp, Matthias</dc:contributor>
    <dc:language>eng</dc:language>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-11-23T13:19:16Z</dc:date>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-11-23T13:19:16Z</dcterms:available>
    <dcterms:abstract xml:lang="eng">Accurate simulations of atomistic systems from first principles are limited by computational cost. In high-throughput settings, machine learning can reduce these costs significantly by accurately interpolating between reference calculations. For this, kernel learning approaches crucially require a representation that accommodates arbitrary atomistic systems. We introduce a many-body tensor representation that is invariant to translations, rotations, and nuclear permutations of same elements, unique, differentiable, can represent molecules and crystals, and is fast to compute. Empirical evidence for competitive energy and force prediction errors is presented for changes in molecular structure, crystal chemistry, and molecular dynamics using kernel regression and symmetric gradient-domain machine learning as models. Applicability is demonstrated for phase diagrams of Pt-group/transition-metal binary systems.</dcterms:abstract>
    <dc:contributor>Huo, Haoyan</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/59261"/>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
URL der Originalveröffentl.
Prüfdatum der URL
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Unbekannt
Diese Publikation teilen