Evaluation of performance of machine learning methods in mining structure-property data of halide perovskite materials  

作　　者：Ruoting Zhao Bangyu Xing Huimin Mu Yuhao Fu Lijun Zhang 赵若廷;邢邦昱;穆慧敏;付钰豪;张立军(State Key Laboratory of Integrated Optoelectronics,Key Laboratory of Automobile Materials of MOE,Jilin Provincial International Cooperation Key Laboratory of High-Efficiency Clean Energy Materials,Electron Microscopy Center,and School of Materials Science and Engineering,Jilin University,Changchun 130012,China;State Key Laboratory of Superhard Materials,College of Physics,Jilin University,Changchun 130012,China;International Center of Computational Method and Software,Jilin University,Changchun 130012,China)

机构地区：[1]State Key Laboratory of Integrated Optoelectronics,Key Laboratory of Automobile Materials of MOE,Jilin Provincial International Cooperation Key Laboratory of High-Efficiency Clean Energy Materials,Electron Microscopy Center,and School of Materials Science and Engineering,Jilin University,Changchun 130012,China [2]State Key Laboratory of Superhard Materials,College of Physics,Jilin University,Changchun 130012,China [3]International Center of Computational Method and Software,Jilin University,Changchun 130012,China

出　　处：《Chinese Physics B》2022年第5期28-35,共8页中国物理B（英文版）

基　　金：supported by the National Natural Science Foundation of China(Grants Nos.62125402 and 92061113)。

摘　　要：With the rapid development of artificial intelligence and machine learning(ML)methods,materials science is rapidly entering the era of data-driven materials informatics.ML models serve as the most crucial component,closely bridging material structure and material properties.There is a considerable difference in the prediction performance of different ML methods for material systems.Herein,we evaluated three categories(linear,kernel,and nonlinear methods)of models,with twelve ML algorithms commonly used in the materials field.In addition,halide perovskite was chosen as an example to evaluate the fitting performance of different models.We constructed a total dataset of 540 halide perovskites and 72 features,with formation energy and bandgap as target properties.We found that different categories of ML models show similar trends for different target properties.Among them,the difference between the models is enormous for the formation energy,with the coefficient of determination(R2)range 0.69-0.953.The fitting performance between the models is closer for bandgap,with the R^(2)range 0.941-0.997.The nonlinear-ensemble model shows the best fitting performance for both the formation energy and the bandgap.It shows that the nonlinear-ensemble model,constructed by combining multiple weak learners,effectively describes the nonlinear relationship between material features and target property.In addition,the extreme gradient boosting decision tree model shows the most superior results among all the models and searches for two new descriptors that are crucial for formation energy and bandgap.Our work provides useful guidance for the selection of effective machine learning methods in the data-mining studies of specific material systems.

关 键 词：machine learning material informatics first-principles calculations halide perovskites 

分 类 号：TB34[一般工业技术—材料科学与工程] TP18[自动化与计算机技术—控制理论与控制工程]