A Machine Learning Approach for Metal Oxide Based Polymer Composites as Charge Selective Layers in Perovskite Solar Cells

A library of metal oxide-conjugated polymer composites was prepared, encompassing WO3 -polyaniline (PANI), -poly(N-methylaniline) (PMANI), -poly(2-fluoroaniline) (PFANI), -polythiophene (PTh), -polyfuran (PFu) and -poly(3,4-ethylenedioxythiophene) (PEDOT) which were used as hole selective layers for perovskite solar cells (PSCs) fabrication. We adopted machine learning approaches to predict compare PSCs performances with the developed its composites. For evaluation performance, a decision tree model that returns 0.9656 R2 score is ideal -PEDOT composite, while random forest found be suitable -PMANI, -PFANI, -PFu scores 0.9976, 0.9968, 0.9772 respectively. In case , -PANI, -PTh, K-Nearest Neighbors 0.9975, 0.9916, 0.9969 Machine can pioneering prediction performance validation.