Applications of Machine Learning in Exploration of the Perovskite Solar Cells

The fusion of machine learning (ML) with material science has catalyzed a revolutionary shift in the discovery and optimization of materials for solar energy applications. This survey paper consolidates the findings from recent studies that leverage ML to navigate the vast chemical space of perovskites, and organic photovoltaic (OPV) materials. These studies under-score ML's potential to predict material properties, accelerate the identification of novel compounds, and optimize their application in solar cells. The summarized research highlights significant advancements in addressing the challenges of efficiency, stability, and environmental safety in solar technology. However, a conspicuous gap in translating these computational discoveries to scalable and environmentally sustainable applications persists, underscoring the need for an integrated approach that encompasses the scalability of synthesized materials, their economic viability, and environmental impact assessment. This paper aims to provide a comprehensive overview of the current state of ML applications in material discovery for solar energy, outline the successes and limitations of recent studies, and delineate a path forward that bridges the gap between theoretical discovery and practical, sustainable application.