{"title":"Automated machine learning guides discovery of ABO3-type oxides for effective water splitting photocatalysis","authors":"Ling Zhang, Guo-xiang Chen, Ze-lin Wang, Xiao-nan Liang, Qi Zhang, Shuai Liu","doi":"10.1016/j.cplett.2025.142034","DOIUrl":null,"url":null,"abstract":"<div><div>The search for suitable perovskite oxides for water splitting is challenging due to their vast compositional space. This study employs the TPOT automated machine learning approach to predict the photocatalytic properties of 5329 ABO<sub>3</sub>-type perovskite oxides based on 14 features. The process streamlines the steps typically associated with conventional machine learning, reducing computational time by 90 % compared to DFT and narrowing the screening scope. Regression and classification models were developed to predict band edge positions and band gap types. Following TPOT optimization, the prediction error was reduced by 42.4 %. Finally, 57 candidate materials were identified, providing potential for experimental synthesis.</div></div>","PeriodicalId":273,"journal":{"name":"Chemical Physics Letters","volume":"869 ","pages":"Article 142034"},"PeriodicalIF":2.8000,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chemical Physics Letters","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0009261425001745","RegionNum":3,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0
Abstract
The search for suitable perovskite oxides for water splitting is challenging due to their vast compositional space. This study employs the TPOT automated machine learning approach to predict the photocatalytic properties of 5329 ABO3-type perovskite oxides based on 14 features. The process streamlines the steps typically associated with conventional machine learning, reducing computational time by 90 % compared to DFT and narrowing the screening scope. Regression and classification models were developed to predict band edge positions and band gap types. Following TPOT optimization, the prediction error was reduced by 42.4 %. Finally, 57 candidate materials were identified, providing potential for experimental synthesis.
期刊介绍：
Chemical Physics Letters has an open access mirror journal, Chemical Physics Letters: X, sharing the same aims and scope, editorial team, submission system and rigorous peer review.
Chemical Physics Letters publishes brief reports on molecules, interfaces, condensed phases, nanomaterials and nanostructures, polymers, biomolecular systems, and energy conversion and storage.
Criteria for publication are quality, urgency and impact. Further, experimental results reported in the journal have direct relevance for theory, and theoretical developments or non-routine computations relate directly to experiment. Manuscripts must satisfy these criteria and should not be minor extensions of previous work.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
