Show simple item record

dc.contributor.authorRosenbrock, CW
dc.contributor.authorHomer, ER
dc.contributor.authorCsányi, G
dc.contributor.authorHart, GLW
dc.date.accessioned2018-12-15T00:30:36Z
dc.date.available2018-12-15T00:30:36Z
dc.date.issued2017-08-03
dc.identifier.issn2057-3960
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/286989
dc.description.abstractMachine learning has proven to be a valuable tool to approximate functions in high-dimensional spaces. Unfortunately, analysis of these models to extract the relevant physics is never as easy as applying machine learning to a large data set in the first place. Here we present a description of atomic systems that generates machine learning representations with a direct path to physical interpretation. As an example, we demonstrate its usefulness as a universal descriptor of grain boundary systems. Grain boundaries in crystalline materials are a quintessential example of a complex, high-dimensional system with broad impact on many physical properties including strength, ductility, corrosion resistance, crack resistance, and conductivity. In addition to modeling such properties, the method also provides insight into the physical "building blocks" that influence them. This opens the way to discover the underlying physics behind behaviors by understanding which building blocks map to particular properties. Once the structures are understood, they can then be optimized for desirable behaviors.
dc.publisherSpringer Science and Business Media LLC
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleDiscovering the building blocks of atomic systems using machine learning: Application to grain boundaries
dc.typeArticle
prism.issueIdentifier1
prism.publicationDate2017
prism.publicationNamenpj Computational Materials
prism.volume3
dc.identifier.doi10.17863/CAM.34298
dcterms.dateAccepted2017-06-12
rioxxterms.versionofrecord10.1038/s41524-017-0027-x
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2017-12-01
dc.identifier.eissn2057-3960
rioxxterms.typeJournal Article/Review
pubs.funder-project-idEngineering and Physical Sciences Research Council (EP/L014742/1)
cam.issuedOnline2017-08-03


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

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