Machine learning-assisted molecular design and efficiency prediction for high-performance organic photovoltaic materials

doi:10.1126/sciadv.aay4275

	Machine learning-assisted molecular design and efficiency prediction for high-performance organic photovoltaic materials
	Sun, Wenbo 5; Zheng, Yujie 5; Yang, Ke 5; Zhang, Qi 5; Shah, Akeel A.5; Wu, Zhou 6; Sun, Yuyang 6; Feng, Liang 1; Chen, Dongyang 2; Xiao, Zeyun 4
刊名	SCIENCE ADVANCES
	2019-11-01
卷号	5 期号:11 页码:8
ISSN号	2375-2548
DOI	10.1126/sciadv.aay4275
通讯作者	Xiao, Zeyun(xiao.z@cigit.ac.cn) ; Lu, Shirong(lushirong@cigit.ac.cn) ; Sun, Kuan(kuan.sun@cqu.edu.cn)
英文摘要	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.
资助项目	National Youth Thousand Program Project[R52A199Z11] ; National Special Funds for Repairing and Purchasing Scientific Institutions[Y72Z090Q10] ; National Natural Science Foundation of China[21801238] ; CAS Pioneer Hundred Talents Program B[Y92A010Q10] ; Natural Science Foundation of Chongqing[cstc2018jcyjAX0556] ; Natural Science Foundation of Chongqing[cstc2017rgzn-zdyfX0030] ; Natural Science Foundation of Chongqing[cstc2017jcyjAX0451] ; Natural Science Foundation of Chongqing[cstc2017rgznzdyfX0023] ; Natural Science Foundation of Chongqing[cstc2018jszxcyzd0603]
WOS研究方向	Science & Technology - Other Topics
语种	英语
出版者	AMER ASSOC ADVANCEMENT SCIENCE
WOS记录号	WOS:000499736100095
内容类型	期刊论文
源URL	[http://119.78.100.138/handle/2HOD01W0/10004]
专题	中国科学院重庆绿色智能技术研究院
通讯作者	Xiao, Zeyun; Lu, Shirong; Sun, Kuan
作者单位	1.Chongqing Univ, Coll Comp Sci, Chongqing 400044, Peoples R China 2.North China Univ Sci & Technol, Sch Elect Engn, 21 Bohaidadao, Tangshan 063210, Hebei, Peoples R China 3.Chongqing Univ, Coll Econ & Business Adm, 174 Shazhengjie, Chongqing 400044, Peoples R China 4.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, 266 Fang Zheng Rd, Chongqing 400714, Peoples R China 5.Chongqing Univ, Sch Energy & Power Engn, MOE Key Lab Low Grade Energy Utilizat Technol & S, 174 Shazhengjie, Chongqing 400044, Peoples R China 6.Chongqing Univ, Sch Automat, MOE Key Lab Dependable Serv Comp Cyber Phys Soc, Chongqing 400044, Peoples R China
推荐引用方式 GB/T 7714	Sun, Wenbo,Zheng, Yujie,Yang, Ke,et al. Machine learning-assisted molecular design and efficiency prediction for high-performance organic photovoltaic materials[J]. SCIENCE ADVANCES,2019,5(11):8.
APA	Sun, Wenbo.,Zheng, Yujie.,Yang, Ke.,Zhang, Qi.,Shah, Akeel A..,...&Sun, Kuan.(2019).Machine learning-assisted molecular design and efficiency prediction for high-performance organic photovoltaic materials.SCIENCE ADVANCES,5(11),8.
MLA	Sun, Wenbo,et al."Machine learning-assisted molecular design and efficiency prediction for high-performance organic photovoltaic materials".SCIENCE ADVANCES 5.11(2019):8.