Machine Learning-Assisted Polymer Design for Improving the Performance of Non-Fullerene Organic Solar Cells

Despite the progress in machine learning (ML) in terms of prediction of power conversion efficiency (PCE) in organic photovoltaics (OPV), the effectiveness of ML in practical applications is still lacking owing to the complex structure-property relationship. Therefore, verifying the potential of ML through experiments can amplify the use of ML models. Herein, we developed a new series of pi-conjugated polymers comprising benzodithiophene and thiazolothiazole with fluorination and alkylthio chains (PBDTTzBO, PFSBDTTzBO, and PFBDTTzBO) for non-fullerene (NF) acceptors based on our random-forest ML model for OPVs. Notably, the order of the ML-predicted PCEs of these polymers with IT-4F (9.93, 11.35, and 11.47%) was in good agreement with their experimental PCEs (5.24, 7.35, and 10.30%). In contrast, an inverse correlation was observed between the predicted (9.20, 12.29, and 12.20%) and experimental (11.98, 1.57, and 6.53%) PCEs with Y6. Both the findings are interpreted in terms of surface morphology, transient photoconductivity, charge carrier mobility, polymer orientation, and miscibility, quantified by the Flory-Huggins parameters. Herein, we present an ML-assisted polymer design for high-performance non-fullerene organic photovoltaics (NFOPVs) and elucidate the importance of the subtle alterations in the morphology of NFOPVs.

Automated summary

This study verifies the potential of machine learning models in organic photovoltaics through experiments and develops a new series of polymers for non-fullerene organic photovoltaics. The experimental results demonstrate a good agreement between the predictions of the machine learning models and the actual performance. The study also explains this consistency through parameters such as surface morphology, photoconductivity, and charge carrier mobility.