Efficient Screening Framework For Organic Solar Cells With Deep Learning And Ensemble Learning

This article presents an automated framework for predicting the power conversion efficiencies (PCEs) of organic solar cells (OSCs). The framework combines an ensemble learning model and a deep learning model to predict the PCEs based on the molecular structure. The ensemble learning model was trained using a small dataset of high-quality experimental data, while the deep learning model was trained using a large dataset of molecular structures and properties. The performance of the framework was verified by experimental results, showing that it can provide direct, fast, and accurate prediction of PCEs.