Show simple item record

dc.contributor.authorGrisafi, Andrea
dc.contributor.authorWilkins, David M
dc.contributor.authorCsányi, Gábor
dc.contributor.authorCeriotti, Michele
dc.date.accessioned2018-12-15T00:30:23Z
dc.date.available2018-12-15T00:30:23Z
dc.date.issued2018-01-19
dc.identifier.issn0031-9007
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/286982
dc.description.abstractStatistical learning methods show great promise in providing an accurate prediction of materials and molecular properties, while minimizing the need for computationally demanding electronic structure calculations. The accuracy and transferability of these models are increased significantly by encoding into the learning procedure the fundamental symmetries of rotational and permutational invariance of scalar properties. However, the prediction of tensorial properties requires that the model respects the appropriate geometric transformations, rather than invariance, when the reference frame is rotated. We introduce a formalism that extends existing schemes and makes it possible to perform machine learning of tensorial properties of arbitrary rank, and for general molecular geometries. To demonstrate it, we derive a tensor kernel adapted to rotational symmetry, which is the natural generalization of the smooth overlap of atomic positions kernel commonly used for the prediction of scalar properties at the atomic scale. The performance and generality of the approach is demonstrated by learning the instantaneous response to an external electric field of water oligomers of increasing complexity, from the isolated molecule to the condensed phase.
dc.format.mediumPrint
dc.languageeng
dc.publisherAmerican Physical Society (APS)
dc.rightsAll rights reserved
dc.titleSymmetry-Adapted Machine Learning for Tensorial Properties of Atomistic Systems.
dc.typeArticle
prism.issueIdentifier3
prism.publicationDate2018
prism.publicationNamePhys Rev Lett
prism.startingPage036002
prism.volume120
dc.identifier.doi10.17863/CAM.34291
dcterms.dateAccepted2017-12-05
rioxxterms.versionofrecord10.1103/PhysRevLett.120.036002
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2018-01
dc.contributor.orcidGrisafi, Andrea [0000-0003-1433-125X]
dc.contributor.orcidWilkins, David M [0000-0003-3739-5512]
dc.identifier.eissn1079-7114
dc.publisher.urlhttp://dx.doi.org/10.1103/PhysRevLett.120.036002
rioxxterms.typeJournal Article/Review
cam.issuedOnline2018-01-19


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record