Your browser doesn't support javascript.
loading
Crystal graph attention networks for the prediction of stable materials.
Schmidt, Jonathan; Pettersson, Love; Verdozzi, Claudio; Botti, Silvana; Marques, Miguel A L.
Afiliación
  • Schmidt J; Institut für Physik, Martin-Luther-Universität Halle-Wittenberg, 06120 Halle (Saale), Germany.
  • Pettersson L; Department of Physics, Lund University Box 118, 221 00 Lund, Sweden.
  • Verdozzi C; Department of Physics, Lund University Box 118, 221 00 Lund, Sweden.
  • Botti S; Institut für Festkörpertheorie und Optik and European Theoretical Spectroscopy Facility, Friedrich-Schiller-Universität Jena, D-07743 Jena, Germany.
  • Marques MAL; Institut für Physik, Martin-Luther-Universität Halle-Wittenberg, 06120 Halle (Saale), Germany.
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

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