Machine learning aided design of perovskite oxide materials for photocatalytic water splitting

作     者：Qiuling Tao Tian Lu Ye Sheng Long Li Wencong Lu Minjie Li Qiuling Tao;Tian Lu;Ye Sheng;Long Li;Wencong Lu;Minjie Li

作者机构：Department of ChemistryCollege of SciencesShanghai UniversityShanghai 200444China Materials Genome InstituteShanghai UniversityShanghai 200444China 

出 版 物：《Journal of Energy Chemistry》 (能源化学（英文版）)

年 卷 期：2021年第30卷第9期

页      面：351-359页

核心收录：

学科分类：12[管理学] 081702[工学-化学工艺] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081705[工学-工业催化] 081104[工学-模式识别与智能系统] 08[工学] 0817[工学-化学工程与技术] 080502[工学-材料学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Financial support to this work from the National Key Research and Development Program of China (No. 2016YFB0700504) the Science and Technology Commission of Shanghai Municipality (18520723500) is gratefully acknowledged 

主　　题：Perovskite Machine learning Online web service Photocatalytic water splitting Bandgap Hydrogen production rate 

摘      要：Suffering from the inefficient traditional trial-and-error methods and the huge searching space filled by millions of candidates, discovering new perovskite visible photocatalysts with higher hydrogen production rate(RH_(2)) still remains a challenge in the field of photocatalytic water splitting(PWS). Herein, we established structural-property models targeted to RH_(2) and the proper bandgap(Eg) via machine learning(ML) technology to accelerate the discovery of efficient perovskite photocatalysts for PWS. The Pearson correlation coefficients(R) of leave-one-out cross validation(LOOCV) were adopted to compare the performances of different algorithms including gradient boosting regression(GBR), support vector regression(SVR), backpropagation artificial neural network(BPANN), and random forest(RF). It was found that the BPANN model showed the highest R values from LOOCV and testing data of 0.9897 and 0.9740 for RH_(2),while the GBR model had the best values of 0.9290 and 0.9207 for Eg. Furtherly, 14 potential PWS perovskite candidates were screened out from 30,000 ABO3-type perovskite structures under the criteria of structural stability, Eg, conduction band energy, valence band energy and RH_(2). The average RH_(2) of these14 perovskites is 6.4% higher than the highest value in the training data set. Moreover, the online web servers were developed to share our prediction models, which could be accessible in http://***/ocpmdm/material_api/ahfga3d9puqlknig(E_g prediction) and http://***/ocpmdm/material_api/i0 ucuyn3 wsd14940(RH_(2) prediction).