High-efficient <i>ab initio</i> Bayesian active learning method and applications in prediction of two-dimensional functional materials
Xingyu Ma, Hou-Yi Lyu, Kuan-Rong Hao, Zhen‐Gang Zhu, Qing‐Bo Yan, Gang Su
Abstract
calculations to accelerate the prediction of desired functional materials with ultrahigh efficiency and accuracy. We apply it as an instance to a large family (3119) of two-dimensional hexagonal binary compounds with unbalanced materials properties, and accurately screen out the materials with maximal electric polarization and proper photovoltaic band gaps, respectively, whereas the computational costs are significantly reduced by only calculating a few tenths of the possible candidates in comparison with a random search. This approach shows the enormous advantages for the cases with unbalanced distribution of target properties. It can be readily applied to seek a broad range of advanced materials.