Predicting Perovskite Bandgap and Solar Cell Performance with Machine Learning

Perovskites as a semiconductor are of profound interest and arguably, the investigation on the distinctive perovskite composition is paramount to fabricate efficient devices and solar cells. We probed the role of anion and cations and their impact on optoelectronic and photovoltaic properties. We report a machine learning approach to predict the bandgap and power conversion efficiency by employing eight different perovskites compositions. The predicted solar cell parameters validate the experimental data. The adopted Random forest model presented a good match with high R² scores of >0.99 and >0.82 for predicted absorption and J-V data sets respectively and showed minimal error rates with precise prediction of bandgap and power conversion efficiencies. Our results suggest that the machine learning technique is an innovative approach to aid the preparation of perovskite and can accelerate the commercial aspects of perovskite solar cells without fabricating working devices and minimizes the fabrication steps and save cost.