Interpretable machine learning predictions for efficient perovskite solar cell development

Perovskite solar cells (PSCs) offer a promising avenue for renewable energy due to their ease of preparation, high energy conversion efficiency, and environmental friendliness. However, the traditional trial-and-error approach in preparing high-efficiency PSCs is inefficient. To address this, our study introduces a goal-driven approach that integrates machine learning and data mining techniques to rapidly screen high-efficiency PSCs based on key features. By successfully predicting high-efficiency PSCs and identifying the dominant factors affecting their performance, namely the perovskite bandgap and the total thickness of the electron transport layer (ETL), this research provides valuable insights for optimizing preparation processes and advancing the development of high-efficiency PSCs, thus significantly contributing to the renewable energy sector.