ホーム > 研究活動 > 2018年 > Crystal structure prediction accelerated by Bayesian optimization

研究活動

Crystal structure prediction accelerated by Bayesian optimization

Physical Review Materials 2, 013803 (2018)

2018年1月9日(火)

Tomoki Yamashita, Nobuya Sato, Hiori Kino, Takashi Miyake, Koji Tsuda, and Tamio Oguchi ( https://doi.org/10.1103/PhysRevMaterials.2.013803 )

Abstract

We propose a crystal structure prediction method based on Bayesian optimization. Our methodis classified as a selection-type algorithm which is different from evolution-type algorithmssuch as an evolutionary algorithm and particle swarm optimization. Crystal structure predictionwith Bayesian optimization can efficiently select the most stable structure from a large numberof candidate structures with a lower number of searching trials using a machine learningtechnique. Crystal structure prediction using Bayesian optimization combined with randomsearch is applied to known systems such as NaCl and Y2Co17 to discuss the efficiency ofBayesian optimization. These results demonstrate that Bayesian optimization can significantlyreduce the number of searching trials required to find the global minimum structure by 30–40%in comparison with pure random search, which leads to much less computational cost. 

その他特記事項

MI^2I, CDMSI 


研究活動

文部科学省

文部科学省
元素戦略プロジェクト(活動紹介)
NIMS磁石パートナーシップ

元素戦略拠点

触媒・電池元素戦略拠点
触媒・電池元素戦略研究拠点 (京都大学)
東工大元素戦略拠点
東工大元素戦略拠点 (東京工業大学)
構造材料元素戦略研究拠点
構造材料元素戦略研究拠点 (京都大学)
高効率モーター用磁性材料技術研究組合
高効率モーター用 磁性材料技術研究組合