Show simple item record

dc.contributor.author Ye, Weike
dc.contributor.author Chen, Chi
dc.contributor.author Wang, Zhenbin
dc.contributor.author Chu, Iek-Heng
dc.contributor.author Ong, Shyue Ping
dc.date.accessioned 2018-10-19T20:53:53Z
dc.date.available 2018-10-19T20:53:53Z
dc.date.issued 2018-09-18
dc.identifier doi:10.5061/dryad.760r5b6
dc.identifier.citation Ye W, Chen C, Wang Z, Chu I, Ong SP (2018) Deep neural networks for accurate predictions of crystal stability. Nature Communications 9: 3800.
dc.identifier.uri http://hdl.handle.net/10255/dryad.190311
dc.description Predicting the stability of crystals is one of the central problems in materials science. Today, density functional theory (DFT) calculations remain comparatively expensive and scale poorly with system size. Here we show that deep neural networks utilizing just two descriptors—the Pauling electronegativity and ionic radii—can predict the DFT formation energies of C3A2D3O12 garnets and ABO3 perovskites with low mean absolute errors (MAEs) of 7–10 meV atom−1 and 20–34 meV atom−1, respectively, well within the limits of DFT accuracy. Further extension to mixed garnets and perovskites with little loss in accuracy can be achieved using a binary encoding scheme, addressing a critical gap in the extension of machine-learning models from fixed stoichiometry crystals to infinite universe of mixed-species crystals. Finally, we demonstrate the potential of these models to rapidly transverse vast chemical spaces to accurately identify stable compositions, accelerating the discovery of novel materials with potentially superior properties.
dc.relation.haspart doi:10.5061/dryad.760r5b6/1
dc.relation.isreferencedby doi:10.1038/s41467-018-06322-x
dc.subject Materials Science
dc.subject Crystal Stability
dc.subject Garnet
dc.subject Perovskite
dc.subject Machine Learning
dc.title Data from: Deep neural networks for accurate predictions of crystal stability
dc.type Article
dc.contributor.correspondingAuthor Ong, Shyue Ping
prism.publicationName Nature Communications
dryad.fundingEntity ACI-1053575@National Science Foundation (United States)
dryad.dansTransferDate 2019-02-11T23:50:31.731+0000
dryad.dansEditIRI https://easy.dans.knaw.nl/sword2/container/27bc3f76-42c1-4d50-b6f9-85c2f94d4aae
dryad.dansArchiveDate 2019-02-12T01:01:35.389+0000
dryad.dashTransferDate 2019-06-25T16:32:32.439+0000
dryad.dashStoredDate 2019-07-19T14:29:29.724+0000

Files in this package

Content in the Dryad Digital Repository is offered "as is." By downloading files, you agree to the Dryad Terms of Service. To the extent possible under law, the authors have waived all copyright and related or neighboring rights to this data. CC0 (opens a new window) Open Data (opens a new window)

Title CrystalDNN
Downloaded 88 times
Description Python scripts, models and data used to predict the formation energies(Ef) and to calculate the energies above hull(Ehull) of garnet and perovskite crystals accompanying the above publication.
Download CrystalDNN.zip (54.98 Mb)
Download README.pdf (100.0 Kb)
Details View File Details

Search for data

Be part of Dryad

We encourage organizations to: