Crystal graph attention networks for the prediction of stable materials.
Sci Adv
; 7(49): eabi7948, 2021 Dec 03.
Article
en En
| MEDLINE
| ID: mdl-34860548
Graph neural networks for crystal structures typically use the atomic positions and the atomic species as input. Unfortunately, this information is not available when predicting new materials, for which the precise geometrical information is unknown. We circumvent this problem by replacing the precise bond distances with embeddings of graph distances. This allows our networks to be applied directly in high-throughput studies based on both composition and crystal structure prototype without using relaxed structures as input. To train these networks, we curate a dataset of over 2 million density functional calculations of crystals with consistent calculation parameters. We apply the resulting model to the high-throughput search of 15 million tetragonal perovskites of composition ABCD2. As a result, we identify several thousand potentially stable compounds and demonstrate that transfer learning from the newly curated dataset reduces the required training data by 50%.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Tipo de estudio:
Prognostic_studies
/
Risk_factors_studies
Idioma:
En
Revista:
Sci Adv
Año:
2021
Tipo del documento:
Article
País de afiliación:
Alemania
Pais de publicación:
Estados Unidos