Show simple item record

dc.contributor.authorSivaraman, Ganesh
dc.contributor.authorKrishnamoorthy, Anand Narayanan
dc.contributor.authorBaur, Matthias
dc.contributor.authorHolm, Christian
dc.contributor.authorStan, Marius
dc.contributor.authorCsányi, Gábor
dc.contributor.authorBenmore, Chris
dc.contributor.authorVázquez-Mayagoitia, Álvaro
dc.date.accessioned2021-02-12T17:31:01Z
dc.date.available2021-02-12T17:31:01Z
dc.date.issued2020-07-23
dc.date.submitted2019-11-04
dc.identifier.others41524-020-00367-7
dc.identifier.other367
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/317570
dc.descriptionFunder: DOE, Office of Science, DE-AC02-06CH11357
dc.description.abstractAbstract: We propose an active learning scheme for automatically sampling a minimum number of uncorrelated configurations for fitting the Gaussian Approximation Potential (GAP). Our active learning scheme consists of an unsupervised machine learning (ML) scheme coupled with a Bayesian optimization technique that evaluates the GAP model. We apply this scheme to a Hafnium dioxide (HfO2) dataset generated from a “melt-quench” ab initio molecular dynamics (AIMD) protocol. Our results show that the active learning scheme, with no prior knowledge of the dataset, is able to extract a configuration that reaches the required energy fit tolerance. Further, molecular dynamics (MD) simulations performed using this active learned GAP model on 6144 atom systems of amorphous and liquid state elucidate the structural properties of HfO2 with near ab initio precision and quench rates (i.e., 1.0 K/ps) not accessible via AIMD. The melt and amorphous X-ray structural factors generated from our simulation are in good agreement with experiment. In addition, the calculated diffusion constants are in good agreement with previous ab initio studies.
dc.languageen
dc.publisherNature Publishing Group UK
dc.rightsAttribution 4.0 International (CC BY 4.0)en
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subjectArticle
dc.subject/639/301/1034/1035
dc.subject/639/301/119/1002
dc.subject/639/301/1005/1008
dc.subject/639/301/923/614
dc.subjectarticle
dc.titleMachine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide
dc.typeArticle
dc.date.updated2021-02-12T17:31:01Z
prism.issueIdentifier1
prism.publicationNamenpj Computational Materials
prism.volume6
dc.identifier.doi10.17863/CAM.64683
dcterms.dateAccepted2020-06-22
rioxxterms.versionofrecord10.1038/s41524-020-00367-7
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by/4.0/
dc.contributor.orcidSivaraman, Ganesh [0000-0001-9056-9855]
dc.contributor.orcidBaur, Matthias [0000-0002-4589-3813]
dc.contributor.orcidVázquez-Mayagoitia, Álvaro [0000-0002-1415-6300]
dc.identifier.eissn2057-3960
pubs.funder-project-idDeutsche Forschungsgemeinschaft (German Research Foundation) (EXC 310)


Files in this item

Thumbnail
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)