Abstract
In the recent years, machine learning (ML) has emerged as a promising tool in delivering fundamental understanding of materials, or predicting new candidate material combinations out from the gigantic chemical combinatorial space. In this talk, I will give a brief overview on the applications of machine learning to atomistic scale simulations of materials. I will discuss our recent works on studying the microstructures of complex perovskites materials, complex ultra elastic alloys, and battery materials. The strengths and weakness of these ML approaches will be addressed. In addition to ML-enabled atomistic simulations using classical computers, I will also briefly discuss our recent progresses in extending the atomistic ML prediction models to quantum circuits.