Machine learning assisted designing of hole-transporting materials for high performance perovskite solar cells

IF 2 3区化学 Q4 CHEMISTRY, PHYSICAL

Chemical Physics Pub Date : 2024-11-12 DOI:10.1016/j.chemphys.2024.112515

Muhammad Saqib , Uzma Shoukat , Mohamed Mohamed Soliman , Shahida Bashir , Mudassir Hussain Tahir , Hamdy Khamees Thabet , Mohamed Kallel

{"title":"Machine learning assisted designing of hole-transporting materials for high performance perovskite solar cells","authors":"Muhammad Saqib , Uzma Shoukat , Mohamed Mohamed Soliman , Shahida Bashir , Mudassir Hussain Tahir , Hamdy Khamees Thabet , Mohamed Kallel","doi":"10.1016/j.chemphys.2024.112515","DOIUrl":null,"url":null,"abstract":"<div><div>In recent years, the advancement of perovskite solar cells has accelerated, leading to continuous performance improvements. Over the past few years, machine learning (ML) has gained popularity among scientists researching perovskite solar cells. In this study, ML is used to screen hole-transporting materials for perovskite solar cells. To construct machine-learning (ML) models, data from prior investigations are collected. Out of four machine learning algorithms trained for predicting reorganization energy (Rh), the gradient boosting regression model stood out as the most effective, attaining an R<sup>2</sup> value of 0.89. Data visualization analysis is then utilized to scrutinize the patterns within the dataset. 10,000 new compounds are generated. Chemical space of generated compounds is visualized using various measures. Minor structural modifications resulted in only a slight alteration in reorganization energy (Rh). The newly introduced multidimensional framework has the potential to efficiently screen materials in a short amount of time.</div></div>","PeriodicalId":272,"journal":{"name":"Chemical Physics","volume":"589 ","pages":"Article 112515"},"PeriodicalIF":2.0000,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chemical Physics","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0301010424003446","RegionNum":3,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}

引用次数: 0

Abstract

In recent years, the advancement of perovskite solar cells has accelerated, leading to continuous performance improvements. Over the past few years, machine learning (ML) has gained popularity among scientists researching perovskite solar cells. In this study, ML is used to screen hole-transporting materials for perovskite solar cells. To construct machine-learning (ML) models, data from prior investigations are collected. Out of four machine learning algorithms trained for predicting reorganization energy (Rh), the gradient boosting regression model stood out as the most effective, attaining an R² value of 0.89. Data visualization analysis is then utilized to scrutinize the patterns within the dataset. 10,000 new compounds are generated. Chemical space of generated compounds is visualized using various measures. Minor structural modifications resulted in only a slight alteration in reorganization energy (Rh). The newly introduced multidimensional framework has the potential to efficiently screen materials in a short amount of time.

查看原文本刊更多论文

机器学习辅助设计用于高性能过氧化物太阳能电池的空穴传输材料

近年来，包晶体太阳能电池的发展日新月异，性能不断提高。在过去几年中，机器学习（ML）在研究包晶体太阳能电池的科学家中越来越受欢迎。在本研究中，ML 被用于筛选包晶体太阳能电池的空穴传输材料。为了构建机器学习（ML）模型，收集了先前研究的数据。在为预测重组能（Rh）而训练的四种机器学习算法中，梯度提升回归模型最为有效，其 R2 值达到 0.89。然后，利用数据可视化分析仔细研究数据集中的模式。生成 10,000 个新化合物。使用各种测量方法对生成化合物的化学空间进行可视化。微小的结构修改仅导致重组能（Rh）的轻微变化。新引入的多维框架具有在短时间内高效筛选材料的潜力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Chemical Physics 化学-物理：原子、分子和化学物理

CiteScore

4.60

自引率

4.30%

发文量

278

审稿时长

39 days

期刊介绍： Chemical Physics publishes experimental and theoretical papers on all aspects of chemical physics. In this journal, experiments are related to theory, and in turn theoretical papers are related to present or future experiments. Subjects covered include: spectroscopy and molecular structure, interacting systems, relaxation phenomena, biological systems, materials, fundamental problems in molecular reactivity, molecular quantum theory and statistical mechanics. Computational chemistry studies of routine character are not appropriate for this journal.