Research Director

Atsuto Seko

Department of Materials Science and Engineering, Kyoto University
Associate Professor

Outline

Descriptors play a crucial role in the construction of machine-learning prediction models of physical properties aimed at accelerating materials design. In this study, simple descriptors for crystal structure that are applicable to a wide range of physical properties will be developed. I will dedicate myself to proposing first-principles machine-learning interatomic potentials of a wide range of materials and constructing prediction models of first-principles physical properties.