Predicting materials properties without crystal structure: deep representation learning from stoichiometry
Publication Date
2020-12-08Journal Title
Nature Communications
Publisher
Nature Publishing Group UK
Volume
11
Issue
1
Language
en
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Goodall, R. E. A., & Lee, A. A. (2020). Predicting materials properties without crystal structure: deep representation learning from stoichiometry. Nature Communications, 11 (1) https://doi.org/10.1038/s41467-020-19964-7
Abstract
Abstract: Machine learning has the potential to accelerate materials discovery by accurately predicting materials properties at a low computational cost. However, the model inputs remain a key stumbling block. Current methods typically use descriptors constructed from knowledge of either the full crystal structure — therefore only applicable to materials with already characterised structures — or structure-agnostic fixed-length representations hand-engineered from the stoichiometry. We develop a machine learning approach that takes only the stoichiometry as input and automatically learns appropriate and systematically improvable descriptors from data. Our key insight is to treat the stoichiometric formula as a dense weighted graph between elements. Compared to the state of the art for structure-agnostic methods, our approach achieves lower errors with less data.
Keywords
Article, /639/638/563/983, /639/301, /639/301/1034/1037, article
Identifiers
s41467-020-19964-7, 19964
External DOI: https://doi.org/10.1038/s41467-020-19964-7
This record's URL: https://www.repository.cam.ac.uk/handle/1810/314901
Rights
Attribution 4.0 International (CC BY 4.0)
Licence URL: https://creativecommons.org/licenses/by/4.0/
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.