Machine learning for accelerating the discovery of high-performance donor/acceptor pairs in non-fullerene organic solar cells

Yao Wu,Jie Min,Rui Sun,Jie Guo

doi:10.1038/s41524-020-00388-2

Abstract

Integrating artificial intelligence (AI) and computer science together with current approaches in material synthesis and optimization will act as an effective approach for speeding up the discovery of high-performance photoactive materials in organic solar cells (OSCs). Yet, like model selection in statistics, the choice of appropriate machine learning (ML) algorithms plays a vital role in the process of new material discovery in databases. In this study, we constructed five common algorithms, and introduced 565 donor/acceptor (D/A) combinations as training data sets to evaluate the practicalities of these ML algorithms and their application potential when guiding material design and D/A pairs screening. Thus, the best predictive capabilities are provided by using the random forest (RF) and boosted regression trees (BRT) approaches beyond other ML algorithms in the data set. Furthermore, >32 million D/A pairs were screened and calculated by RF and BRT models, respectively. Among them, six photovoltaic D/A pairs are selected and synthesized to compare their predicted and experimental power conversion efficiencies. The outcome of ML and experiment verification demonstrates that the RF approach can be effectively applied to high-throughput virtual screening for opening new perspectives to design of materials and D/A pairs, thereby accelerating the development of OSCs.

Highlights

In the latest decade, the discovery of novel photoactive donor (D) and acceptor (A) materials has greatly promoted the development of bulk heterojunction (BHJ) organic solar cells (OSCs)[1,2,3,4,5,6,7]
Data of 88 D/A pairs were served as testing set to evaluate the predictive capability of models based on the five algorithms, which are introduced from Microsoft Azure machine learning (ML) studio for predicting power conversion efficiency (PCE). (4) The models computed ~32,076,000 potential D/A pairs, from the results of which, six new D/A pairs are selected by experiments to further confirm the performance of ML methods in screening counterpart for active layer materials
Relevant D/A pairs and their photovoltaic performance work as important references for manual designing of materials and for ML

Summary

Introduction

The discovery of novel photoactive donor (D) and acceptor (A) materials has greatly promoted the development of bulk heterojunction (BHJ) organic solar cells (OSCs)[1,2,3,4,5,6,7]. In this process, tens of thousands of photovoltaic materials have been designed and synthesized by chemists and materials scientists. To reduce the consumption of trial and error experiments and accelerate the discovery of high-performance materials, developing strategies based on shortening the lifecycle of material development will become extremely important in the future research of OSCs

Methods

Results

Conclusion