Molecular structural descriptor-assisted machine learning for organic photovoltaics with perylenediimide acceptors

IF 1.7 4区 化学 Bulletin of the Korean Chemical Society Pub Date : 2023-12-15 DOI:10.1002/bkcs.12810
Gyu-Hee Kim, Keonho Yoon, Chihyung Lee, Minwoo Nam, Doo-Hyun Ko
{"title":"Molecular structural descriptor-assisted machine learning for organic photovoltaics with perylenediimide acceptors","authors":"Gyu-Hee Kim,&nbsp;Keonho Yoon,&nbsp;Chihyung Lee,&nbsp;Minwoo Nam,&nbsp;Doo-Hyun Ko","doi":"10.1002/bkcs.12810","DOIUrl":null,"url":null,"abstract":"<p>Although organic photovoltaics (OPVs) have evolved over the last two decades, the discovery of new materials and optimization of numerous considerations for high-performance devices remain challenging. To reduce these laborious processes and expedite the advancement of OPVs, we constructed machine learning (ML) models that predict photovoltaic parameters. We designed a unique descriptor that divides the molecular structure into smaller units and translates them into a concise matrix. This allows the ML model to easily track structural units and understand which units are important for predicting target performance, enabling the ML model to prioritize crucial units. Therefore, without requiring additional data from measurements or calculations, the ML models can extract chemical properties from molecular structural information and accurately predict the photovoltaic parameters. The ML models that predict the photovoltaic parameters, including the open-circuit voltage, short-circuit current density, fill factor, and power conversion efficiency, all show remarkably superior prediction performance, with Pearson correlation coefficients exceeding 0.68. Consequently, in this article, we propose a highly precise and reliable predictive OPV-ML platform that can robustly screen for unnecessary experiments and accelerate OPV development.</p>","PeriodicalId":54252,"journal":{"name":"Bulletin of the Korean Chemical Society","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2023-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bulletin of the Korean Chemical Society","FirstCategoryId":"92","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/bkcs.12810","RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Although organic photovoltaics (OPVs) have evolved over the last two decades, the discovery of new materials and optimization of numerous considerations for high-performance devices remain challenging. To reduce these laborious processes and expedite the advancement of OPVs, we constructed machine learning (ML) models that predict photovoltaic parameters. We designed a unique descriptor that divides the molecular structure into smaller units and translates them into a concise matrix. This allows the ML model to easily track structural units and understand which units are important for predicting target performance, enabling the ML model to prioritize crucial units. Therefore, without requiring additional data from measurements or calculations, the ML models can extract chemical properties from molecular structural information and accurately predict the photovoltaic parameters. The ML models that predict the photovoltaic parameters, including the open-circuit voltage, short-circuit current density, fill factor, and power conversion efficiency, all show remarkably superior prediction performance, with Pearson correlation coefficients exceeding 0.68. Consequently, in this article, we propose a highly precise and reliable predictive OPV-ML platform that can robustly screen for unnecessary experiments and accelerate OPV development.

Abstract Image

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用分子结构描述符辅助机器学习过二亚胺受体的有机光伏技术
尽管有机光伏(OPV)在过去二十年中不断发展,但发现新材料和优化高性能设备的诸多考虑因素仍然充满挑战。为了减少这些费力的过程并加快 OPV 的发展,我们构建了机器学习 (ML) 模型来预测光伏参数。我们设计了一种独特的描述符,可将分子结构划分为更小的单元,并将其转化为简洁的矩阵。这使得 ML 模型能够轻松跟踪结构单元,并了解哪些单元对预测目标性能非常重要,从而使 ML 模型能够优先考虑关键单元。因此,无需额外的测量或计算数据,ML 模型就能从分子结构信息中提取化学特性,并准确预测光伏参数。预测光伏参数(包括开路电压、短路电流密度、填充因子和功率转换效率)的 ML 模型均显示出显著的预测性能,皮尔逊相关系数超过 0.68。因此,在本文中,我们提出了一个高度精确和可靠的 OPV-ML 预测平台,该平台可以有力地筛选不必要的实验,加速 OPV 的开发。
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 去求助
来源期刊
Bulletin of the Korean Chemical Society
Bulletin of the Korean Chemical Society Chemistry-General Chemistry
自引率
23.50%
发文量
182
期刊介绍: The Bulletin of the Korean Chemical Society is an official research journal of the Korean Chemical Society. It was founded in 1980 and reaches out to the chemical community worldwide. It is strictly peer-reviewed and welcomes Accounts, Communications, Articles, and Notes written in English. The scope of the journal covers all major areas of chemistry: analytical chemistry, electrochemistry, industrial chemistry, inorganic chemistry, life-science chemistry, macromolecular chemistry, organic synthesis, non-synthetic organic chemistry, physical chemistry, and materials chemistry.
期刊最新文献
Masthead Cover Picture: Synthesis and computational studies for halide-free, neutral, and bifunctional one-component ferrocene-based catalysts for the coupling of carbon dioxide and epoxides (BKCS 10/2024) Jieun Lee, Wooram Lee, Yoseph Kim, Mujin Choi, Seol Ryu, Joonkyung Jang, Youngjo Kim Cost-effective synthesis of unsymmetric tetrazines Moisture-resistant nitroaromatic explosive gas sensor based on hydrophilic pentiptycene polymer Synthesis and computational studies for halide-free, neutral, and bifunctional one-component ferrocene-based catalysts for the coupling of carbon dioxide and epoxides
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1