Identifying domains of applicability of machine learning models for materials science

Machine learning models insufficient for certain screening tasks can still provide valuable predictions in specific sub-domains of the considered materials. Here, the authors introduce a diagnostic tool to detect regions of low expected model error as demonstrated for the case of transparent conduct...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Christopher Sutton, Mario Boley, Luca M. Ghiringhelli, Matthias Rupp, Jilles Vreeken, Matthias Scheffler
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
Q
Acceso en línea:https://doaj.org/article/9eb779b7ce2346bab2bcf81c05b1f1a9
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:9eb779b7ce2346bab2bcf81c05b1f1a9
record_format dspace
spelling oai:doaj.org-article:9eb779b7ce2346bab2bcf81c05b1f1a92021-12-02T19:09:54ZIdentifying domains of applicability of machine learning models for materials science10.1038/s41467-020-17112-92041-1723https://doaj.org/article/9eb779b7ce2346bab2bcf81c05b1f1a92020-09-01T00:00:00Zhttps://doi.org/10.1038/s41467-020-17112-9https://doaj.org/toc/2041-1723Machine learning models insufficient for certain screening tasks can still provide valuable predictions in specific sub-domains of the considered materials. Here, the authors introduce a diagnostic tool to detect regions of low expected model error as demonstrated for the case of transparent conducting oxides.Christopher SuttonMario BoleyLuca M. GhiringhelliMatthias RuppJilles VreekenMatthias SchefflerNature PortfolioarticleScienceQENNature Communications, Vol 11, Iss 1, Pp 1-9 (2020)
institution DOAJ
collection DOAJ
language EN
topic Science
Q
spellingShingle Science
Q
Christopher Sutton
Mario Boley
Luca M. Ghiringhelli
Matthias Rupp
Jilles Vreeken
Matthias Scheffler
Identifying domains of applicability of machine learning models for materials science
description Machine learning models insufficient for certain screening tasks can still provide valuable predictions in specific sub-domains of the considered materials. Here, the authors introduce a diagnostic tool to detect regions of low expected model error as demonstrated for the case of transparent conducting oxides.
format article
author Christopher Sutton
Mario Boley
Luca M. Ghiringhelli
Matthias Rupp
Jilles Vreeken
Matthias Scheffler
author_facet Christopher Sutton
Mario Boley
Luca M. Ghiringhelli
Matthias Rupp
Jilles Vreeken
Matthias Scheffler
author_sort Christopher Sutton
title Identifying domains of applicability of machine learning models for materials science
title_short Identifying domains of applicability of machine learning models for materials science
title_full Identifying domains of applicability of machine learning models for materials science
title_fullStr Identifying domains of applicability of machine learning models for materials science
title_full_unstemmed Identifying domains of applicability of machine learning models for materials science
title_sort identifying domains of applicability of machine learning models for materials science
publisher Nature Portfolio
publishDate 2020
url https://doaj.org/article/9eb779b7ce2346bab2bcf81c05b1f1a9
work_keys_str_mv AT christophersutton identifyingdomainsofapplicabilityofmachinelearningmodelsformaterialsscience
AT marioboley identifyingdomainsofapplicabilityofmachinelearningmodelsformaterialsscience
AT lucamghiringhelli identifyingdomainsofapplicabilityofmachinelearningmodelsformaterialsscience
AT matthiasrupp identifyingdomainsofapplicabilityofmachinelearningmodelsformaterialsscience
AT jillesvreeken identifyingdomainsofapplicabilityofmachinelearningmodelsformaterialsscience
AT matthiasscheffler identifyingdomainsofapplicabilityofmachinelearningmodelsformaterialsscience
_version_ 1718377105599758336