Application of machine learning methods for predicting new superhard materials
- 17 August 2020
- journal article
- conference paper
- Published by AIP Publishing in Journal of Applied Physics
- Vol. 128 (7) , 075102
Abstract
Superhard materials are of great interest in various practical applications, and an increasing number of research efforts are focused on their development. In this article, we demonstrate that machine learning can be successfully applied to searching for such materials. We construct a machine learning model using neural networks on graphs together with a recently developed physical model of hardness and fracture toughness. The model is trained using available elastic data from the Materials Project database and has good accuracy for predictions. We use this model to screen all crystal structures in the database and systematize all the promising hard or superhard materials, and find that diamond (and its polytypes) are the hardest materials in the database. Our results can be further used for the investigation of interesting materials using more accurate ab initio calculations and/or experiments.Keywords
Funding Information
- Russian Science Foundation (19-72-30043)
This publication has 42 references indexed in Scilit:
- Modeling hardness of polycrystalline materials and bulk metallic glassesIntermetallics, 2011
- Transparent dense sodiumNature, 2009
- Electronegativity Identification of Novel Superhard MaterialsPhysical Review Letters, 2008
- High-Pressure Phases of SilanePhysical Review Letters, 2006
- Hardness of Covalent and Ionic Crystals: First-Principle CalculationsPhysical Review Letters, 2006
- Bonding Changes in Compressed Superhard GraphiteScience, 2003
- Hardness of Covalent CrystalsPhysical Review Letters, 2003
- Self-Consistent Equations Including Exchange and Correlation EffectsPhysical Review B, 1965
- Inhomogeneous Electron GasPhysical Review B, 1964
- The Elastic Behaviour of a Crystalline AggregateProceedings of the Physical Society. Section A, 1952