Simple Structural Descriptor Obtained from Symbolic Classification for Predicting the Oxygen Vacancy Defect Formation of Perovskites
Siyu Liu, Jing Wang, Zhongtao Duan, Kongxiang Wang, Wanlu Zhang, Ruiqian Guo, Fengxian Xie
Abstract
Symbolic classification is an approach of interpretable machine learning for building mathematical formulas that fit certain data sets. In this work, symbolic classification is used to establish the relationship between oxygen vacancy defect formation energy and structural features. We find a structural descriptor na(ra/Ena – rb), where na is the valence of the a-site ion, ra is the radius of the a-site ion, Ena is the electronegativity of the a-site ion, and rb is the radius of the b-site ion. It accelerates the screening of defect-free oxide perovskites in advance of density functional theory (DFT) calculations and experimental characterization. Our results demonstrate the potential of symbolic classification for accelerating the data-driven design and discovery of materials with improved properties.