[1Fa01-05] Data-driven research and development focused on data generation/storage/analysis: Data-Driven Surface Science Division's Session

[1Fa03] Neural network potential study of complex solid systems

*Koji Shimizu¹, Satoshi Watanabe¹ (1. Department of Materials Engineering, The University of Tokyo)

Machine-learning of interatomic potentials using data from first-principles calculations has been actively discussed in the field of data-driven materials science. By employing the high-dimensional neural network potential (NNP), we have been working on its applications and developments. In this talk, we will present our applications of NNPs in Au-Li binary systems and a few other topics. Furthermore, we will illustrate our proposed NN model to analyze the point defect behavior in multiple charge states using wurzite-GaN. Additionally, we will also demonstrate Li motion under electric fields in both crystalline and amorphous Li₃PO₄ structures.