Machine Learning–Based Prediction of Organic Solar Cell Performance Using Molecular Descriptors

The performance of Organic Solar Cells (OSCs) is intrinsically linked to the molecular, electronic, and structural properties of donor and acceptor materials. This study employs various machine learning techniques, namely the Generalized Regression Neural Network (GRNN), Support Vector Machine (SVM), and Tree Boost, to predict key performance metrics of OSCs, including power conversion efficiency (PCE), short-circuit current density (JSC), open-circuit voltage (VOC), and fill factor (FF). The models are trained and evaluated using an experimentally reported dataset compiled by Sahu et al. Correlation analysis demonstrates that material characteristics such as polarizability, bandgap, dipole moment, and charge transfer are statistically associated with OSC performance. The predictive performance of the GRNN model is compared with that of the SVM and Tree Boost models, showing consistently lower prediction errors within the considered dataset. In addition, sensitivity analysis is performed to assess the relative importance of the predictor variables and to examine the influence of kernel functions on GRNN performance. The results indicate that machine learning models, particularly GRNN, can serve as effective data-driven tools for predicting the performance of organic solar cells and for supporting computational screening studies.