Exploration of stable atomic configurations in graphene-like BCN systems by Bayesian optimization

TL;DR

This paper combines first-principles calculations with Bayesian optimization to efficiently identify stable atomic configurations in h-BCN, a material with tunable bandgap, revealing promising semiconductor structures.

Contribution

It introduces a novel encoding method incorporating local atomic environments and domain knowledge, enhancing the search for stable configurations in complex materials.

Findings

Discovered two stable semiconductor configurations in h-BCN

Validated the effectiveness of the encoding method in the search process

Confirmed the embedding of key structural features via principal component analysis

Abstract

h-BCN is an intriguing material system where the bandgap varies considerably depending on the atomic configuration, even at a fixed composition. Exploring stable atomic configurations in this system is crucial for discussing the energetic formability and controllability of desirable configurations. In this study, this challenge is tackled by combining first-principles calculations with Bayesian optimization. An encoding method that represents the configurations as vectors, while incorporating information about the local atomic environments and domain knowledge, is proposed for the search. The proposed encoding method proved effective in the search, resulting in the discovery of two interesting and stable semiconductor configurations. Furthermore, the optimization behavior is discussed through principal component analysis, confirming that the ordered BN network and the C configuration features are well embedded in the search space. While our approach provided a tailored encoding for the h-BCN system in this study, it holds promise for broader application to other materials by adapting the domain knowledge matrix to each target system.