文献类型：期刊文献

英文题名：Deep Learning-Assisted Design of Novel Donor-Acceptor Combinations for Organic Photovoltaic Materials with Enhanced Efficiency

作者：Zhang, Shizhao[1];Li, Shuixing[2];Song, Siqin[1];Zhao, Yang[1];Gao, Liang[1];Chen, Hongzheng[2];Li, Hanying[2];Lin, Jiaping[1]

机构：[1]East China Univ Sci & Technol, Frontiers Sci Ctr Materiobiol & Dynam Chem, Sch Mat Sci & Engn, Shanghai Key Lab Adv Polymer Mat,Key Lab Ultrafine, Shanghai 200237, Peoples R China;[2]Zhejiang Univ, Dept Polymer Sci & Engn, State Key Lab Silicon Mat, MOE Key Lab Macromol Synth & Functionalizat, Hangzhou 310027, Peoples R China

年份：2025

卷号：37

期号：4

外文期刊名：ADVANCED MATERIALS

收录：;EI(收录号：20245017510750);WOS:【SCI-EXPANDED(收录号:WOS:001373917900001)】；

基金：This work was supported by the National Natural Science Foundation of China (52394271 and 22103025) and the Shanghai Chenguang Program (22CGA31).

语种：英文

外文关键词：deep learning; donor-acceptor combinations; high-throughput screen; organic photovoltaic; structural design

摘要：Designing donor (D) and acceptor (A) structures and discovering promising D-A combinations can effectively improve organic photovoltaic (OPV) device performance. However, to obtain excellent power conversion efficiency (PCE), the trial-and-error structural design in the infinite chemical space is time-consuming and costly. Herein, a deep learning (DL)-assisted design framework for OPV materials is proposed. To effectively digitally represent the D and A structures, a structure representation method, polymer fingerprints, is developed, and a database of OPV materials is constructed. By applying an end-to-end graph neural network modeling method, high-precision DL models for predicting OPV performance are established. After combining the existing structures, approximate to 0.6 million virtual D-A combinations are generated. Then, the OPV performance of these candidate combinations is predicted by the well-trained models, and numbers of novel D-A combinations with high efficiency are identified. Experimental validations confirm that the prediction accuracy is greater than 93% and one of the screened combinations (i.e., D18:BTP-S11) exhibits an efficiency above 19.3% in single-junction organic solar cells. Finally, based on the structural gene analysis, the design rules to guide experimental explorations are suggested. The developed DL-assisted approach can accelerate the design of D-A combinations with ultrahigh efficiency and bring property breakthroughs for OPV devices.