EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Machine‐Learning‐Assisted Determination of the Global Zero‐Temperature Phase Diagram of Materials

Jonathan Schmidt iD, Noah Hoffmann, Hai-Chen Wang, Pedro Borlido, Pedro J M A Carriço, Tiago F T Cerqueira, Silvana Botti, Miguel A L Marques

Advanced Materials · 2023-06 · 35 (22)

DOI: 10.1002/adma.202210788 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Materials, online erschienen am 07.04.2023. Verfasst von Jonathan Schmidt und 7 weiteren Autor:innen. Beteiligte Einrichtung: Institut für Physik, Martin-Luther-Universität Halle-Wittenberg, D-06099, Halle, Germany. Die Arbeit wurde bisher 137-mal zitiert (Crossref) und nennt 89 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Gauss Centre for Supercomputing, Fundação para a Ciemcia e Tecnologia Portugal.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

high-throughput density functional theory calculationsmachine learning material sciencematerial discoverysuperconductivitysuperhard materials

Autor:innen und Institutionen

  • Institut für Physik, Martin-Luther-Universität Halle-Wittenberg, D-06099, Halle, Germany.
  • CFisUC, Department of Physics, University of Coimbra, Rua Larga, 3004-516, Coimbra, Portugal.
  • Institut für Festkörpertheorie und -optik, Friedrich-Schiller-Universität Jena, Max-Wien-Platz 1, 07743, Jena, Germany.

ORCID-Profile: Jonathan Schmidt

Förderung

  • Gauss Centre for Supercomputing
  • Fundação para a Ciemcia e Tecnologia Portugal

Zitieren

APA

Schmidt, J., Hoffmann, N., Wang, H. C., Borlido, P., Carriço, P. J. M. A., Cerqueira, T. F. T., Botti, S., & Marques, M. A. L. (2023). Machine‐Learning‐Assisted Determination of the Global Zero‐Temperature Phase Diagram of Materials. Advanced Materials, 35(22). https://doi.org/10.1002/adma.202210788

Vancouver

Schmidt J, Hoffmann N, Wang HC, Borlido P, Carriço PJMA, Cerqueira TFT, et al. Machine‐Learning‐Assisted Determination of the Global Zero‐Temperature Phase Diagram of Materials. Advanced Materials. 2023;35(22). doi:10.1002/adma.202210788

BibTeX
@article{Schmidt2023,
  author = {Schmidt, Jonathan and Hoffmann, Noah and Wang, Hai-Chen and Borlido, Pedro and Carriço, Pedro J M A and Cerqueira, Tiago F T and Botti, Silvana and Marques, Miguel A L},
  title = {Machine‐Learning‐Assisted Determination of the Global Zero‐Temperature Phase Diagram of Materials},
  journal = {Advanced Materials},
  year = {2023},
  volume = {35},
  number = {22},
  doi = {10.1002/adma.202210788}
}
Kostenlos starten →