{"title":"Hybrid approach for simulating graded PeDA-DJ perovskite solar cells: SCAPS-1D and machine learning","authors":"Shivani Gohri, Jaya Madan, Rahul Pandey","doi":"10.1016/j.cplett.2025.141897","DOIUrl":null,"url":null,"abstract":"<div><div>This work utilized graded DJ-perovskite ((PeDA)(MA)<sub>n-1</sub>Pb<sub>n</sub>I<sub>3n+1</sub>) solar cells (GDJPSC), whose bandgap can be changed by changing the number of inorganic layers(n). The power-law-graded absorber layer minimizes the transmission and thermalization losses, enhancing the absorption of the sun spectrum. Further, GDJPSC performance is analyzed, viz. thickness, bulk defect density, and interface defect densities. Thereafter, different machine learning (ML) algorithms are used to train and test the model, which helps predict the efficiency of GDJPSC by reducing the use of extensive resources and computational timings. Results reported that XGB performance is best among all the ML models with the means square error of 0 and R<sup>2</sup> value of 0.99.</div></div>","PeriodicalId":273,"journal":{"name":"Chemical Physics Letters","volume":"863 ","pages":"Article 141897"},"PeriodicalIF":2.8000,"publicationDate":"2025-01-16","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/S0009261425000375","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
This work utilized graded DJ-perovskite ((PeDA)(MA)n-1PbnI3n+1) solar cells (GDJPSC), whose bandgap can be changed by changing the number of inorganic layers(n). The power-law-graded absorber layer minimizes the transmission and thermalization losses, enhancing the absorption of the sun spectrum. Further, GDJPSC performance is analyzed, viz. thickness, bulk defect density, and interface defect densities. Thereafter, different machine learning (ML) algorithms are used to train and test the model, which helps predict the efficiency of GDJPSC by reducing the use of extensive resources and computational timings. Results reported that XGB performance is best among all the ML models with the means square error of 0 and R2 value of 0.99.
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
