Stability forecasting of perovskite solar cells utilizing various machine learning and deep learning techniques

In this study, we propose the use of Machine Learning (ML) and Neural Network (NN) techniques for forecasting the stability of Perovskite Solar Cells (PSCs). We gather experimental data from various studies and examine the impact of environmental conditions on stability degradation. Our research stands out for its innovative approach in employing three distinct techniques: Support Vector Machine (SVM), Multilayer Perceptron Regression (MLPR), and Probabilistic Neural Networks (PNN). Each method is rigorously evaluated using the same dataset, showcasing the robustness and reliability of our analysis. Notably, the incorporation of extreme environmental conditions data and the adoption of the PNN technique are the key contributions of this research. Our results indicate that the PNN technique achieves the highest accuracy with an evaluation score of 70.17