Hybrid algorithm of Bayesian optimization and evolutionary algorithm in crystal structure prediction. Issue 1 (31st December 2022)

• Record Type: Journal Article
• Authors: Yamashita, Tomoki; Kino, Hiori; Tsuda, Koji; Miyake, Takashi; Oguchi, Tamio
• Is Part Of: Science and Technology of Advanced Materials: Methods. Volume 2:Issue 1(2022)
• Page Start: 67
• Page End: 74
• Publication Date: 2022-12-31
• Subjects: Crystal structure prediction -- Bayesian optimization -- evolutionary algorithm -- first-principles calculations -- machine learning -- materials informatics
• DOI: 10.1080/27660400.2022.2055987
• Languages: English
• ISSNs: 2766-0400

Abstract

ABSTRACT: We propose a highly efficient searching algorithm in crystal structure prediction. The searching algorithm is a hybrid of the evolutionary algorithm and Bayesian optimization. The evolutionary algorithm is widely used in crystal structure prediction, and the Bayesian optimization is one of the selection-type algorithms we have developed. We have performed simulations of crystal structure prediction to compare the success rates of the random search, evolutionary algorithm, Bayesian optimization, and hybrid algorithm for up to ternary systems such as Si, Y2 Co17, Al2 O3, and CuGaS2, using the CrySPY code. These results demonstrate that the evolutionary algorithm can generate structures more efficiently than random structure generation, and the Bayesian optimization can efficiently select potential candidates from a large number of structures. Moreover, the hybrid algorithm, which has the advantages of both, is proved to be the most efficient searching algorithm among them. GRAPHICAL ABSTRACT: uf0001