Please use this identifier to cite or link to this item:
https://hdl.handle.net/10316/107111
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Schmidt, Jonathan | - |
dc.contributor.author | Hoffmann, Noah | - |
dc.contributor.author | Wang, Hai-Chen | - |
dc.contributor.author | Borlido, Pedro | - |
dc.contributor.author | Carriço, Pedro J. M. A. | - |
dc.contributor.author | Cerqueira, Tiago F. T. | - |
dc.contributor.author | Botti, Silvana | - |
dc.contributor.author | Marques, Miguel A. L. | - |
dc.date.accessioned | 2023-05-12T13:01:33Z | - |
dc.date.available | 2023-05-12T13:01:33Z | - |
dc.date.issued | 2023-03-22 | - |
dc.identifier.issn | 0935-9648 | - |
dc.identifier.issn | 1521-4095 | - |
dc.identifier.uri | https://hdl.handle.net/10316/107111 | - |
dc.description.abstract | Crystal-graph attention neural networks have emerged recently as remarkable tools for the prediction of thermodynamic stability. The efficacy of their learning capabilities and their reliability is however subject to the quantity and quality of the data they are fed. Previous networks exhibit strong biases due to the inhomogeneity of the training data. Here a high-quality dataset is engineered to provide a better balance across chemical and crystal-symmetry space. Crystal-graph neural networks trained with this dataset show unprecedented generalization accuracy. Such networks are applied to perform machine-learning-assisted high-throughput searches of stable materials, spanning 1 billion candidates. In this way, the number of vertices of the global T = 0 K phase diagram is increased by 30% and find more than ≈150 000 compounds with a distance to the convex hull of stability of less than 50 meV atom-1 . The discovered materials are then accessed for applications, identifying compounds with extreme values of a few properties, such as superconductivity, superhardness, and giant gap-deformation potentials. | pt |
dc.description.sponsorship | The authors gratefully acknowledge the Gauss Centre for Supercomputing e.V. (www.gauss-centre.eu) for funding this project by providing computing time on the GCS Supercomputer SUPERMUC-NG at Leibniz Supercomputing Centre (www.lrz.de) under the project pn25co. T.F.T.C., P.J.M.A.C., and P.B. acknowledge financial support from FCT - Fundação para a Ciência e Tecnologia, Portugal (projects UIDB/04564/2020 and UIDP/04564/2020 and contract 2020.04225.CEECIND) and computational resources provided by the Laboratory for Advanced Computing at University of Coimbra.Open access funding enabled and organized by Projekt DEAL | pt |
dc.language.iso | eng | pt |
dc.publisher | Wiley | pt |
dc.relation | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UID/FIS/4564/2016/PT/Centro de Física da Universidade de Coimbra | pt |
dc.relation | info:eu-repo/grantAgreement/FCT/CEEC IND 3ed/2020.04225.CEECIND/CP1609/CT0016/PT/Not available | pt |
dc.rights | openAccess | pt |
dc.rights.uri | http://creativecommons.org/licenses/by-nc/4.0/ | pt |
dc.subject | high-throughput density functional theory calculations | pt |
dc.subject | machine learning material science | pt |
dc.subject | material discovery | pt |
dc.subject | superconductivity | pt |
dc.subject | superhard materials | pt |
dc.title | Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials | pt |
dc.type | article | pt |
degois.publication.firstPage | e2210788 | pt |
degois.publication.title | Advanced Materials | pt |
dc.relation.publisherversion | https://onlinelibrary.wiley.com/doi/epdf/10.1002/adma.202210788 | pt |
dc.peerreviewed | yes | pt |
dc.identifier.doi | 10.1002/adma.202210788 | - |
dc.date.embargo | 2023-03-22 | * |
dc.identifier.pmid | 36949007 | - |
uc.date.periodoEmbargo | 0 | pt |
dc.identifier.eissn | 1521-4095 | - |
item.cerifentitytype | Publications | - |
item.languageiso639-1 | en | - |
item.fulltext | Com Texto completo | - |
item.grantfulltext | open | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.openairetype | article | - |
crisitem.author.researchunit | CFisUC – Center for Physics of the University of Coimbra | - |
crisitem.author.researchunit | CFisUC – Center for Physics of the University of Coimbra | - |
crisitem.author.researchunit | CFisUC – Center for Physics of the University of Coimbra | - |
Appears in Collections: | I&D CFis - Artigos em Revistas Internacionais |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Advanced Materials - 2023 - Schmidt - Machine‐Learning‐Assisted Determination of the Global Zero‐Temperature Phase Diagram.pdf | 1.49 MB | Adobe PDF | View/Open |
SCOPUSTM
Citations
8
checked on May 20, 2024
WEB OF SCIENCETM
Citations
7
checked on May 2, 2024
Page view(s)
77
checked on May 21, 2024
Download(s)
17
checked on May 21, 2024
Google ScholarTM
Check
Altmetric
Altmetric
This item is licensed under a Creative Commons License