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, Keonho Yoon, Chihyung Lee, Minwoo Nam, 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":"45 2","pages":"125-130"},"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.
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.