Crystal Structure Prediction by Bayesian Optimization and Evolutionary Algorithm

Crystal structure prediction methods such as random search (RS) and evolutionary algorithm (EA) have attracted attention. Previously we have developed a searching algorithm accelerated by Bayesian optimization (BO). BO is a selection-type algorithm which can efficiently select potential candidates by machine learning. First, we compared searching efficiency among RS, EA, and BO in the small system of Si₁₆. In each algorithm, a hundred structures were searched. The importance of random generation is found compared with evolutionary operations even in EA. RS could be the most efficient for small systems. Furthermore, we develop a hybrid algorithm of BO and EA, and discuss the searching efficiency in large systems.