Improved Predictions of Organic Photovoltaic Performance through Machine Learning Models Empowered by Artificially Generated Failure Data

The conventional development of organic photovoltaic (OPV) materials has been driven by the inspiration and continuous endeavors of experimentalists, whereas machine learning (ML) approaches enable extremely high-throughput data processing. However, the predictive accuracy of ML currently remains insufficient for the design of OPV semiconductors that exhibit a complex connectivity between chemical structure and power conversion efficiency (PCE). In this study, we examined the impact of data selection and the introduction of artificially generated failure data on ML predictions of polymer/non-fullerene, small-molecular-acceptor (NFA) solar cells. We demonstrated that an ML model empowered by artificially generated failure data (∼0% PCE by insoluble polymers based on an inappropriate choice of solubilizing side alkyl chains) led to improved predictions. This approach was validated through the synthesis and characterization of twelve polymers (benzothiadiazole, thienothiophene, or tetrazine coupled with benzodithiophene; benzobisthiazole coupled with dioxo-benzodithiophene). Our work offers a facile approach to mitigate the difficulties of the ML-driven development of OPV materials that is also readily applicable to other material science fields.