Machine learning force fields based on local parametrization of dispersion interactions: Application to the phase diagram of C60

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorMuhli, Heikkien_US
dc.contributor.authorChen, Xien_US
dc.contributor.authorBartók, Albert P.en_US
dc.contributor.authorHernández-León, Patriciaen_US
dc.contributor.authorCsányi, Gáboren_US
dc.contributor.authorAla-Nissila, Tapioen_US
dc.contributor.authorCaro, Miguel A.en_US
dc.contributor.departmentDepartment of Applied Physicsen
dc.contributor.departmentDepartment of Electrical Engineering and Automationen
dc.contributor.groupauthorMultiscale Statistical and Quantum Physicsen
dc.contributor.groupauthorComputational Electronic Structure Theoryen
dc.contributor.groupauthorComputational Soft and Molecular Matteren
dc.contributor.groupauthorMicrosystems Technologyen
dc.contributor.groupauthorCentre of Excellence in Quantum Technology, QTFen
dc.contributor.organizationUniversity of Warwicken_US
dc.contributor.organizationUniversity of Cambridgeen_US
dc.date.accessioned2021-08-25T06:50:49Z
dc.date.available2021-08-25T06:50:49Z
dc.date.issued2021-08-06en_US
dc.descriptionFunding Information: The authors acknowledge funding from the Academy of Finland, under Projects No. 310574, No. 330488, and No. 329483 (M.A.C.), 321713 (M.A.C., P.H.-L., and H.M.), No. 308647 (X.C.), No. 314298 (X.C. and H.M.), and the QTF Center of Excellence program Grant No. 312298 (T.A.-N.). M.A.C., P. H.-L., and H.M. also acknowledge a seed funding grant from the Aalto University Materials Platform. Computing time from CSC–IT Center for Science for the MaCaNa project and from Aalto University's Science IT project is gratefully acknowledged. Publisher Copyright: © 2021 American Physical Society.
dc.description.abstractWe present a comprehensive methodology to enable the addition of van der Waals (vdW) corrections to machine learning (ML) atomistic force fields. Using a Gaussian approximation potential (GAP) [Bartók et al., Phys. Rev. Lett. 104, 136403 (2010)10.1103/PhysRevLett.104.136403] as a baseline, we accurately machine learn a local model of atomic polarizabilities based on Hirshfeld volume partitioning of the charge density [Tkatchenko and Scheffler, Phys. Rev. Lett. 102, 073005 (2009)10.1103/PhysRevLett.102.073005]. These environment-dependent polarizabilities are then used to parametrize a screened London-dispersion approximation to the vdW interactions. Our ML vdW model only needs to learn the charge density partitioning implicitly by learning the reference Hirshfeld volumes from density functional theory (DFT). In practice, we can predict accurate Hirshfeld volumes from the knowledge of the local atomic environment (atomic positions) alone, making the model highly computationally efficient. For additional efficiency, our ML model of atomic polarizabilities reuses the same many-body atomic descriptors used for the underlying GAP learning of bonded interatomic interactions. We also show how the method enables straightforward computation of gradients of the observables, even when these remain challenging for the reference method (e.g., calculating gradients of the Hirshfeld volumes in DFT). Finally, we demonstrate the approach by studying the phase diagram of C60, where vdW effects are important. The need for a highly accurate vdW-inclusive reactive force field is highlighted by modeling the decomposition of the C60 molecules taking place at high pressures and temperatures.en
dc.description.versionPeer revieweden
dc.format.extent16
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationMuhli, H, Chen, X, Bartók, A P, Hernández-León, P, Csányi, G, Ala-Nissila, T & Caro, M A 2021, ' Machine learning force fields based on local parametrization of dispersion interactions : Application to the phase diagram of C60 ', Physical Review B, vol. 104, no. 5, 054106 . https://doi.org/10.1103/PhysRevB.104.054106en
dc.identifier.doi10.1103/PhysRevB.104.054106en_US
dc.identifier.issn2469-9950
dc.identifier.issn2469-9969
dc.identifier.otherPURE UUID: 2ad62fe4-a52a-4664-8662-d8db895c110een_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/2ad62fe4-a52a-4664-8662-d8db895c110een_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85112024947&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/66690620/Machine_learning_force_fields_based_on_local_parametrization_of_dispersion_interactions.PhysRevB.104.054106.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/109113
dc.identifier.urnURN:NBN:fi:aalto-202108258350
dc.language.isoenen
dc.publisherAmerican Physical Society
dc.relation.ispartofseriesPhysical Review Ben
dc.relation.ispartofseriesVolume 104, issue 5en
dc.rightsopenAccessen
dc.titleMachine learning force fields based on local parametrization of dispersion interactions: Application to the phase diagram of C60en
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionpublishedVersion
Files