A5056741467- Nuclear Physics and Applications
- Machine Learning in Materials Science
- Hydrogen embrittlement and corrosion behaviors in metals
- Electron and X-Ray Spectroscopy Techniques
University of California, Davis
2022
Abstract Advances in machine learning (ML) have enabled the development of interatomic potentials that promise accuracy first principles methods and low-cost, parallel efficiency empirical potentials. However, ML-based struggle to achieve transferability, i.e., provide consistent across configurations differ from those used during training. In order realize potentials, systematic scalable approaches generate diverse training sets need be developed. This work creates a set for tungsten an...
Advances in machine learning (ML) techniques have enabled the development of interatomic potentials that promise both accuracy first principles methods and low-cost, linear scaling, parallel efficiency empirical potentials. Despite rapid progress last few years, ML-based often struggle to achieve transferability, is, provide consistent across configurations significantly differ from those used train model. In order truly realize potentials, it is therefore imperative develop systematic...