Affiliation:
1. Institut für Physik Martin‐Luther‐Universität Halle‐Wittenberg D‐06099 Halle Germany
2. CFisUC Department of Physics University of Coimbra Rua Larga 3004‐516 Coimbra Portugal
3. Institut für Festkörpertheorie und ‐optik Friedrich‐Schiller‐Universität Jena Max‐Wien‐Platz 1 07743 Jena Germany
Abstract
AbstractCrystal‐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.
Subject
Mechanical Engineering,Mechanics of Materials,General Materials Science
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献