Harnessing Machine Learning to Predict and Optimize the Performance of MASnI 3 /FASnI 3 Double‐Absorber Lead‐Free Perovskite Solar Cells

This is the authors' abstract. We don't add key points for this paper.

This work applies machine learning (ML) to predict and optimise the performance of a lead‐free MASnI 3 /FASnI 3 double absorber perovskite solar cell. SCAPS‐1D simulations were performed by varying absorber thickness and doping densities to generate a dataset for training ML models, including Support Vector Regression (SVR), Random Forest (RF), XGBoost (XGB), CatBoostRegressor and a stacked SVR‐RF ensemble. The optimised device achieved a PCE of 28.14%, a J SC of 30.74 mA/cm 2 , a V OC of 1.07 V, and a FF of 86% at 0.5 µm MASnI 3 and 0.3 µm FASnI 3 thicknesses. Among the models, CatBoostRegressor showed the highest accuracy with R 2 = 0.999156 and MSE = 0.002598. Performance evaluation for different training/testing ratios indicated that the 80:20 split gave the best balance between learning and generalisation. A Pearson correlation heatmap and histogram analysis further revealed a strong positive correlation between absorber thickness, J SC , and PCE, validating the ML predictions. The integrated simulation‐ML approach offers a fast and reliable method for designing high‐efficiency, lead‐free perovskite solar cells.