{"title":"借助机器学习为有机太阳能电池设计小分子供体并进行性能预测","authors":"","doi":"10.1016/j.jphotochem.2024.116026","DOIUrl":null,"url":null,"abstract":"<div><p>Designing of materials for organic solar cells is a tedious process. In present study, machine learning (ML) is used to predict the power conversion efficiency (PCE). Over 40 ML models are tried. Gradient boosting regression is appeared as best model. 10k small molecule donors are designed. Their PCE values are predicted using best model. The library of generated donors is visualized using various tools. Chemical similarity analysis is done to study structural behavior of selected donors. Reasonable resemblance is found. Synthetic accessibility assessment has indicated easy synthesis for majority of selected small molecule donors. The introduced framework has ability to find the efficient materials in short time.</p></div>","PeriodicalId":16782,"journal":{"name":"Journal of Photochemistry and Photobiology A-chemistry","volume":null,"pages":null},"PeriodicalIF":4.1000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Designing of small molecule donors with the help of machine learning for organic solar cells and performance prediction\",\"authors\":\"\",\"doi\":\"10.1016/j.jphotochem.2024.116026\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Designing of materials for organic solar cells is a tedious process. In present study, machine learning (ML) is used to predict the power conversion efficiency (PCE). Over 40 ML models are tried. Gradient boosting regression is appeared as best model. 10k small molecule donors are designed. Their PCE values are predicted using best model. The library of generated donors is visualized using various tools. Chemical similarity analysis is done to study structural behavior of selected donors. Reasonable resemblance is found. Synthetic accessibility assessment has indicated easy synthesis for majority of selected small molecule donors. The introduced framework has ability to find the efficient materials in short time.</p></div>\",\"PeriodicalId\":16782,\"journal\":{\"name\":\"Journal of Photochemistry and Photobiology A-chemistry\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.1000,\"publicationDate\":\"2024-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Photochemistry and Photobiology A-chemistry\",\"FirstCategoryId\":\"92\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1010603024005707\",\"RegionNum\":3,\"RegionCategory\":\"化学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Photochemistry and Photobiology A-chemistry","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1010603024005707","RegionNum":3,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0
摘要
有机太阳能电池材料的设计是一个繁琐的过程。在本研究中，机器学习（ML）被用来预测功率转换效率（PCE）。尝试了 40 多个 ML 模型。梯度提升回归被认为是最佳模型。设计了 10k 个小分子供体。使用最佳模型预测它们的 PCE 值。使用各种工具对生成的供体库进行可视化。进行化学相似性分析，研究选定供体的结构行为。结果发现了合理的相似性。合成可及性评估表明，大多数选定的小分子供体易于合成。引入的框架能够在短时间内找到高效的材料。
Designing of small molecule donors with the help of machine learning for organic solar cells and performance prediction
Designing of materials for organic solar cells is a tedious process. In present study, machine learning (ML) is used to predict the power conversion efficiency (PCE). Over 40 ML models are tried. Gradient boosting regression is appeared as best model. 10k small molecule donors are designed. Their PCE values are predicted using best model. The library of generated donors is visualized using various tools. Chemical similarity analysis is done to study structural behavior of selected donors. Reasonable resemblance is found. Synthetic accessibility assessment has indicated easy synthesis for majority of selected small molecule donors. The introduced framework has ability to find the efficient materials in short time.
期刊介绍：
JPPA publishes the results of fundamental studies on all aspects of chemical phenomena induced by interactions between light and molecules/matter of all kinds.
All systems capable of being described at the molecular or integrated multimolecular level are appropriate for the journal. This includes all molecular chemical species as well as biomolecular, supramolecular, polymer and other macromolecular systems, as well as solid state photochemistry. In addition, the journal publishes studies of semiconductor and other photoactive organic and inorganic materials, photocatalysis (organic, inorganic, supramolecular and superconductor).
The scope includes condensed and gas phase photochemistry, as well as synchrotron radiation chemistry. A broad range of processes and techniques in photochemistry are covered such as light induced energy, electron and proton transfer; nonlinear photochemical behavior; mechanistic investigation of photochemical reactions and identification of the products of photochemical reactions; quantum yield determinations and measurements of rate constants for primary and secondary photochemical processes; steady-state and time-resolved emission, ultrafast spectroscopic methods, single molecule spectroscopy, time resolved X-ray diffraction, luminescence microscopy, and scattering spectroscopy applied to photochemistry. Papers in emerging and applied areas such as luminescent sensors, electroluminescence, solar energy conversion, atmospheric photochemistry, environmental remediation, and related photocatalytic chemistry are also welcome.
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
