BIGDML-Towards accurate quantum machine learning force fields for materials
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Sauceda, Huziel E. | - |
dc.contributor.author | Galvez-Gonzalez, Luis E. | - |
dc.contributor.author | Chmiela, Stefan | - |
dc.contributor.author | Oliver Paz-Borbon, Lauro | - |
dc.contributor.author | Mueller, Klaus-Robert | - |
dc.contributor.author | Tkatchenko, Alexandre | - |
dc.date.accessioned | 2022-09-24T11:43:25Z | - |
dc.date.available | 2022-09-24T11:43:25Z | - |
dc.date.created | 2022-09-23 | - |
dc.date.issued | 2022-06-29 | - |
dc.identifier.issn | 2041-1723 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/143881 | - |
dc.description.abstract | Most machine-learning force fields dismiss long-range interactions. Here the authors demonstrate the BIGDML approach for building materials' potential energy surfaces that enables a broad range of materials simulations within accuracies better than 1 meV/atom using just 10-200 structures for training. Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Currently, MLFFs often introduce tradeoffs that restrict their practical applicability to small subsets of chemical space or require exhaustive datasets for training. Here, we introduce the Bravais-Inspired Gradient-Domain Machine Learning (BIGDML) approach and demonstrate its ability to construct reliable force fields using a training set with just 10-200 geometries for materials including pristine and defect-containing 2D and 3D semiconductors and metals, as well as chemisorbed and physisorbed atomic and molecular adsorbates on surfaces. The BIGDML model employs the full relevant symmetry group for a given material, does not assume artificial atom types or localization of atomic interactions and exhibits high data efficiency and state-of-the-art energy accuracies (errors substantially below 1 meV per atom) for an extended set of materials. Extensive path-integral molecular dynamics carried out with BIGDML models demonstrate the counterintuitive localization of benzene-graphene dynamics induced by nuclear quantum effects and their strong contributions to the hydrogen diffusion coefficient in a Pd crystal for a wide range of temperatures. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | NATURE PORTFOLIO | - |
dc.subject | SINGLE-ATOM CATALYSTS | - |
dc.subject | HYDROGEN DIFFUSION | - |
dc.subject | GRAPHENE | - |
dc.subject | 1ST-PRINCIPLES | - |
dc.subject | POTENTIALS | - |
dc.subject | DEPENDENCE | - |
dc.subject | BINDING | - |
dc.title | BIGDML-Towards accurate quantum machine learning force fields for materials | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Mueller, Klaus-Robert | - |
dc.identifier.doi | 10.1038/s41467-022-31093-x | - |
dc.identifier.scopusid | 2-s2.0-85133016527 | - |
dc.identifier.wosid | 000830675000008 | - |
dc.identifier.bibliographicCitation | NATURE COMMUNICATIONS, v.13, no.1 | - |
dc.relation.isPartOf | NATURE COMMUNICATIONS | - |
dc.citation.title | NATURE COMMUNICATIONS | - |
dc.citation.volume | 13 | - |
dc.citation.number | 1 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Science & Technology - Other Topics | - |
dc.relation.journalWebOfScienceCategory | Multidisciplinary Sciences | - |
dc.subject.keywordPlus | SINGLE-ATOM CATALYSTS | - |
dc.subject.keywordPlus | HYDROGEN DIFFUSION | - |
dc.subject.keywordPlus | GRAPHENE | - |
dc.subject.keywordPlus | 1ST-PRINCIPLES | - |
dc.subject.keywordPlus | POTENTIALS | - |
dc.subject.keywordPlus | DEPENDENCE | - |
dc.subject.keywordPlus | BINDING | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.