Liu Siyu, Wang Jing, Duan Zhongtao, Wang Kongxiang, Zhang Wanlu, Guo Ruiqian, Xie Fengxian
Institute of Future Lighting, Academy for Engineering and Technology, Fudan University, Shanghai 200433, China.
Institute for Electric Light Sources, School of Information Science and Technology, Fudan University, Shanghai 200433, China.
ACS Appl Mater Interfaces. 2022 Mar 9;14(9):11758-11767. doi: 10.1021/acsami.1c24003. Epub 2022 Feb 23.
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 (/ - ), where is the valence of the a-site ion, is the radius of the a-site ion, is the electronegativity of the a-site ion, and 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.
符号分类是一种可解释的机器学习方法，用于构建适合特定数据集的数学公式。在这项工作中，符号分类用于建立氧空位缺陷形成能与结构特征之间的关系。我们发现了一个结构描述符（/ - ），其中 是a位离子的化合价， 是a位离子的半径， 是a位离子的电负性， 是b位离子的半径。它在密度泛函理论（DFT）计算和实验表征之前加速了无缺陷氧化物钙钛矿的筛选。我们的结果证明了符号分类在加速数据驱动的具有改进性能的材料设计和发现方面的潜力。
