Adaptive Sampling Methods via Machine Learning for Materials Screening

Science and Technology of Advanced Materials: Methods

Ryo Tamura¹  Yu Kumagai²  Akira Takahashi²  Hirotaka Aoki²  Fumiyasu Oba² 

[1] National Institute for Materials Science;Tokyo Institute of Technology;

关键词: machine learning;    adaptive sampling;    bayesian optimization;    first-principles calculations;   

DOI  :  10.1080/27660400.2022.2039573

来源: DOAJ

【 摘 要 】

High-throughput virtual screening by using a combination of first-principles calculations and Bayesian optimization (BO) has attracted much attention as a method for efficient materials exploration. The purpose of the virtual screening is often to search for the materials whose properties meet a certain target criterion, while the conventional BO aims to find the global extremum. Some recent works use the conventional BO by converting target properties for such motivation. On the other hand, an adaptive sampling method, where the acquisition function is based on the probability that a data point achieves a target property within a specific range, is suggested previously [Kishio et al., Chemom. Intell. Lab. Syst. 127, 70 (2013)]. In this paper, we demonstrate that such adaptive sampling is effective for the exploration of the materials whose properties meet target criteria. We conducted simulations of materials exploration using an in-house database constructed by first-principles calculations and compared the performances of the adaptive sampling and conventional BO approaches. Further, we evaluate and discuss the performances of acquisition functions extended to multi-objective problems for materials exploration considering multiple target properties simultaneously.

【 授权许可】

Unknown