Hybrid algorithm of Bayesian optimization and evolutionary algorithm in crystal structure prediction

• Published in: Science and Technology of Advanced Materials: Methods Vol. 2; no. 1; pp. 67 - 74
• Main Authors: Yamashita, Tomoki, Kino, Hiori, Tsuda, Koji, Miyake, Takashi, Oguchi, Tamio
• Format: Journal Article
• Language: English; Japanese
• Published: Taylor & Francis 31.12.2022; Informa UK Limited; Taylor & Francis Group
• Subjects: Bayesian optimization; Crystal structure prediction; evolutionary algorithm; first-principles calculations; machine learning; materials informatics; Materials of engineering and construction. Mechanics of materials; TA401-492
• ISSN: 2766-0400; 2766-0400
• DOI: 10.1080/27660400.2022.2055987

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, Y 2 Co 17 , Al 2 O 3 , and CuGaS 2 , 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.