Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10316/107111 https://doi.org/10.1002/adma.202210788 |
Resumo: | 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. |
id |
RCAP_e25bedb24abde65e4c8fe7b333180662 |
---|---|
oai_identifier_str |
oai:estudogeral.uc.pt:10316/107111 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materialshigh-throughput density functional theory calculationsmachine learning material sciencematerial discoverysuperconductivitysuperhard materialsCrystal-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.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 DEALWiley2023-03-22info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10316/107111http://hdl.handle.net/10316/107111https://doi.org/10.1002/adma.202210788eng0935-96481521-4095369490071521-4095https://onlinelibrary.wiley.com/doi/epdf/10.1002/adma.202210788Schmidt, JonathanHoffmann, NoahWang, Hai-ChenBorlido, PedroCarriço, Pedro J. M. A.Cerqueira, Tiago F. T.Botti, SilvanaMarques, Miguel A. L.info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-05-12T13:07:08Zoai:estudogeral.uc.pt:10316/107111Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T21:23:28.716218Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials |
title |
Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials |
spellingShingle |
Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials Schmidt, Jonathan high-throughput density functional theory calculations machine learning material science material discovery superconductivity superhard materials |
title_short |
Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials |
title_full |
Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials |
title_fullStr |
Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials |
title_full_unstemmed |
Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials |
title_sort |
Machine-Learning-Assisted Determination of the Global Zero-Temperature Phase Diagram of Materials |
author |
Schmidt, Jonathan |
author_facet |
Schmidt, Jonathan Hoffmann, Noah Wang, Hai-Chen Borlido, Pedro Carriço, Pedro J. M. A. Cerqueira, Tiago F. T. Botti, Silvana Marques, Miguel A. L. |
author_role |
author |
author2 |
Hoffmann, Noah Wang, Hai-Chen Borlido, Pedro Carriço, Pedro J. M. A. Cerqueira, Tiago F. T. Botti, Silvana Marques, Miguel A. L. |
author2_role |
author author author author author author author |
dc.contributor.author.fl_str_mv |
Schmidt, Jonathan Hoffmann, Noah Wang, Hai-Chen Borlido, Pedro Carriço, Pedro J. M. A. Cerqueira, Tiago F. T. Botti, Silvana Marques, Miguel A. L. |
dc.subject.por.fl_str_mv |
high-throughput density functional theory calculations machine learning material science material discovery superconductivity superhard materials |
topic |
high-throughput density functional theory calculations machine learning material science material discovery superconductivity superhard materials |
description |
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. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-03-22 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10316/107111 http://hdl.handle.net/10316/107111 https://doi.org/10.1002/adma.202210788 |
url |
http://hdl.handle.net/10316/107111 https://doi.org/10.1002/adma.202210788 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
0935-9648 1521-4095 36949007 1521-4095 https://onlinelibrary.wiley.com/doi/epdf/10.1002/adma.202210788 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Wiley |
publisher.none.fl_str_mv |
Wiley |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799134121630367744 |