MOE Key Laboratory of Low-grade Energy Utilization Technologies and Systems, School of Energy and Power Engineering, Chongqing University, 174 Shazhengjie, Shapingba, Chongqing 400044, China.
MOE Key Laboratory of Dependable Service Computing in Cyber Physical Society, School of Automation, Chongqing University, Chongqing 400044, China.
Sci Adv. 2019 Nov 8;5(11):eaay4275. doi: 10.1126/sciadv.aay4275. eCollection 2019 Nov.
In the process of finding high-performance materials for organic photovoltaics (OPVs), it is meaningful if one can establish the relationship between chemical structures and photovoltaic properties even before synthesizing them. Here, we first establish a database containing over 1700 donor materials reported in the literature. Through supervised learning, our machine learning (ML) models can build up the structure-property relationship and, thus, implement fast screening of OPV materials. We explore several expressions for molecule structures, i.e., images, ASCII strings, descriptors, and fingerprints, as inputs for various ML algorithms. It is found that fingerprints with length over 1000 bits can obtain high prediction accuracy. The reliability of our approach is further verified by screening 10 newly designed donor materials. Good consistency between model predictions and experimental outcomes is obtained. The result indicates that ML is a powerful tool to prescreen new OPV materials, thus accelerating the development of the OPV field.
在为有机光伏（OPV）寻找高性能材料的过程中，如果能够在合成之前建立化学结构与光伏性能之间的关系，那将是有意义的。在这里，我们首先建立了一个包含 1700 多种文献报道的供体材料的数据库。通过有监督学习，我们的机器学习（ML）模型可以建立结构-性能关系，从而实现 OPV 材料的快速筛选。我们探索了几种分子结构的表示形式，即图像、ASCII 字符串、描述符和指纹，作为各种 ML 算法的输入。结果发现，长度超过 1000 位的指纹可以获得较高的预测精度。通过筛选 10 种新设计的供体材料，进一步验证了我们方法的可靠性。模型预测与实验结果之间得到了很好的一致性。结果表明，机器学习是一种预筛选新型 OPV 材料的有力工具，从而加速了 OPV 领域的发展。
