Data-driven analysis of hysteresis and stability in perovskite solar cells using machine learning

• Machine Learning for PSC Analysis: Leveraged Pearson correlation and random forest models to reveal hidden trends in perovskite solar cell (PSC) stability and hysteresis using data from the extensive Perovskite Database. • Stack-Wide Influence on Hysteresis: Found that PSC hysteresis is influenced more by the entire device stack than by individual materials, with the p-i-n structure significantly reducing hysteresis. • Challenges in Stability Prediction: Stability predictions were limited by inconsistent data reporting, emphasizing the need for standardized testing for improved machine learning model accuracy in PSC stability predictions. • Advancement in AI for Energy Materials: Demonstrates the value of machine learning in uncovering material insights critical to advancing energy applications, especially in enhancing PSC performance and scalability. Perovskite solar cells are promising photovoltaic devices because of the high defect tolerance and desirable optoelectronic properties of the metal-halide perovskite absorber materials. The transition from lab to industry is still an open problem, which is mainly limited by upscaling and stability. In this study we try to use tools from data science namely Pearson correlation and random forest regressor applied to the data from the open-source platform “Perovskite Database” to understand the correlations with material choice, fabrication techniques, and current-voltage key features to the stability and hysteresis index. We find that the cell stack as a whole plays a crucial role in hysteresis and not a single layer. We statistically confirm that p-i-n and higher-efficient solar cells generally show reduced hysteresis. We identify certain cross correlations, which would lead to wrong conclusions e.g. claiming an open-circuit voltage not correlated with the hysteresis or some apparent correlations with material parameters, which originate from the historical development. Regarding stability, we are not able to obtain good performance from the machine learning model. Reasons are non-standardized measurements and lack of sufficient data.