Investigating the Role of Machine Learning and Deep Learning for Determining the Performance of Perovskite-Based Solar Cells

Solar energy presents a promising avenue for renewable energy, despite facing challenges such as low efficiency, instability, and high manufacturing costs. Recently, the photovoltaic (PV) sector has turned to machine learning (ML) techniques due to advancements in computational power, tools, and data availability. This paper explores the implementation of both ML and Deep Learning (DL) techniques with the primary objective of evaluating DL's efficacy in predicting the performance of perovskite solar cells (PSCs). Our findings indicate that with meticulous dataset preprocessing, DL methods show promise in this research domain. While ML algorithms outperformed DL techniques in our study, there exists significant potential for DL in the PV sector.