Show simple item record

dc.contributor.authorAllen, Alice E A
dc.contributor.authorDusson, Geneviève
dc.contributor.authorOrtner, Christoph
dc.contributor.authorCsányi, Gábor
dc.date.accessioned2021-03-08T11:02:51Z
dc.date.available2021-03-08T11:02:51Z
dc.date.issued2021-02-26
dc.date.submitted2020-10-11
dc.identifier.othermlstabd51e
dc.identifier.otherabd51e
dc.identifier.othermlst-100255.r1
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/318493
dc.description.abstractAbstract: We introduce and explore an approach for constructing force fields for small molecules, which combines intuitive low body order empirical force field terms with the concepts of data driven statistical fits of recent machine learned potentials. We bring these two key ideas together to bridge the gap between established empirical force fields that have a high degree of transferability on the one hand, and the machine learned potentials that are systematically improvable and can converge to very high accuracy, on the other. Our framework extends the atomic permutationally invariant polynomials (aPIP) developed for elemental materials in (2019 Mach. Learn.: Sci. Technol. 1 015004) to molecular systems. The body order decomposition allows us to keep the dimensionality of each term low, while the use of an iterative fitting scheme as well as regularisation procedures improve the extrapolation outside the training set. We investigate aPIP force fields with up to generalised 4-body terms, and examine the performance on a set of small organic molecules. We achieve a high level of accuracy when fitting individual molecules, comparable to those of the many-body machine learned force fields. Fitted to a combined training set of short linear alkanes, the accuracy of the aPIP force field still significantly exceeds what can be expected from classical empirical force fields, while retaining reasonable transferability to both configurations far from the training set and to new molecules.
dc.languageen
dc.publisherIOP Publishing
dc.rightsAttribution 4.0 International (CC BY 4.0)en
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subjectPaper
dc.subjectmolecular mechanics
dc.subjectmolecular potentials
dc.subjectforce field parametrization
dc.subjectsmall molecules
dc.titleAtomic permutationally invariant polynomials for fitting molecular force fields
dc.typeArticle
dc.date.updated2021-03-08T11:02:50Z
prism.issueIdentifier2
prism.publicationNameMachine Learning: Science and Technology
prism.volume2
dc.identifier.doi10.17863/CAM.65607
dcterms.dateAccepted2020-12-18
rioxxterms.versionofrecord10.1088/2632-2153/abd51e
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by/4.0
dc.contributor.orcidAllen, Alice E A [0000-0002-8727-8333]
dc.contributor.orcidDusson, Geneviève [0000-0002-7160-6064]
dc.contributor.orcidOrtner, Christoph [0000-0003-1498-8120]
dc.contributor.orcidCsányi, Gábor [0000-0002-8180-2034]
dc.identifier.eissn2632-2153
pubs.funder-project-idLeverhulme Trust (RPG-2017-191)
pubs.funder-project-idInvestissements d’Avenir (ANR-15-IDEX-0003)


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International (CC BY 4.0)
Except where otherwise noted, this item's licence is described as Attribution 4.0 International (CC BY 4.0)