Ultra-fast interpretable machine-learning potentials

Lade...
Vorschaubild
Dateien
Xie_2-1e7lbcqjdgj0f0.pdf
Xie_2-1e7lbcqjdgj0f0.pdfGröße: 1.83 MBDownloads: 2
Datum
2023
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
ArXiv-ID
Internationale Patentnummer
Link zur Lizenz
EU-Projektnummer
952165
DFG-Projektnummer
Angaben zur Forschungsförderung (Freitext)
National Science Foundation: DMR 2118718
National Science Foundation: DMS 1440415
National Science Foundation: DMS-1440415
U.S. Department of Energy: DE-SC0020385
U.S. Department of Energy: DE-SC0020385
EC | Horizon 2020 Framework Programme: 952165
Projekt
Open Access-Veröffentlichung
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Zeitschriftenartikel
Publikationsstatus
Published
Erschienen in
npj Computational Materials. Springer. 2023, 9, 162. eISSN 2057-3960. Available under: doi: 10.1038/s41524-023-01092-7
Zusammenfassung

All-atom dynamics simulations are an indispensable quantitative tool in physics, chemistry, and materials science, but large systems and long simulation times remain challenging due to the trade-off between computational efficiency and predictive accuracy. To address this challenge, we combine effective two- and three-body potentials in a cubic B-spline basis with regularized linear regression to obtain machine-learning potentials that are physically interpretable, sufficiently accurate for applications, as fast as the fastest traditional empirical potentials, and two to four orders of magnitude faster than state-of-the-art machine-learning potentials. For data from empirical potentials, we demonstrate the exact retrieval of the potential. For data from density functional theory, the predicted energies, forces, and derived properties, including phonon spectra, elastic constants, and melting points, closely match those of the reference method. The introduced potentials might contribute towards accurate all-atom dynamics simulations of large atomistic systems over long-time scales.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690XIE, Stephen R., Matthias RUPP, Richard G. HENNIG, 2023. Ultra-fast interpretable machine-learning potentials. In: npj Computational Materials. Springer. 2023, 9, 162. eISSN 2057-3960. Available under: doi: 10.1038/s41524-023-01092-7
BibTex
@article{Xie2023Ultra-69286,
  year={2023},
  doi={10.1038/s41524-023-01092-7},
  title={Ultra-fast interpretable machine-learning potentials},
  volume={9},
  journal={npj Computational Materials},
  author={Xie, Stephen R. and Rupp, Matthias and Hennig, Richard G.},
  note={Article Number: 162}
}
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/123456789/69286">
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/69286/1/Xie_2-1e7lbcqjdgj0f0.pdf"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/69286"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:language>eng</dc:language>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/69286/1/Xie_2-1e7lbcqjdgj0f0.pdf"/>
    <dc:creator>Xie, Stephen R.</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-02-09T07:24:48Z</dc:date>
    <dcterms:abstract>All-atom dynamics simulations are an indispensable quantitative tool in physics, chemistry, and materials science, but large systems and long simulation times remain challenging due to the trade-off between computational efficiency and predictive accuracy. To address this challenge, we combine effective two- and three-body potentials in a cubic B-spline basis with regularized linear regression to obtain machine-learning potentials that are physically interpretable, sufficiently accurate for applications, as fast as the fastest traditional empirical potentials, and two to four orders of magnitude faster than state-of-the-art machine-learning potentials. For data from empirical potentials, we demonstrate the exact retrieval of the potential. For data from density functional theory, the predicted energies, forces, and derived properties, including phonon spectra, elastic constants, and melting points, closely match those of the reference method. The introduced potentials might contribute towards accurate all-atom dynamics simulations of large atomistic systems over long-time scales.</dcterms:abstract>
    <dcterms:issued>2023</dcterms:issued>
    <dc:creator>Hennig, Richard G.</dc:creator>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-02-09T07:24:48Z</dcterms:available>
    <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by/4.0/"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Xie, Stephen R.</dc:contributor>
    <dc:contributor>Hennig, Richard G.</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:title>Ultra-fast interpretable machine-learning potentials</dcterms:title>
    <dc:rights>Attribution 4.0 International</dc:rights>
    <dc:creator>Rupp, Matthias</dc:creator>
    <dc:contributor>Rupp, Matthias</dc:contributor>
  </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
Nein
Begutachtet
Ja
Diese Publikation teilen