[19a-B01-1~10] 23.1 Joint Session N "Informatics"

[19a-B01-1] An Extension of the First-Principles Simulations Using Machine Learning

〇Ryoji Asahi¹, Kazutoshi Miwa¹, Ryosuke Jinnouchi¹, Joohwi Lee¹ (1.Toyota Chuken)

Keywords:first-principles calculation, machine learning, materials design

First-principles simulation based on density functional theory (DFT) can predict several properties and apply to materials design and database construction. On the other hand, DFT calculation is still computationally demanding, and thus desired to be more efficient so that it can apply to a more practical modelling. In this study, we implement machine-learning algorithm with DFT to enhance capability and efficiency without sacrificing accuracy of DFT.