Perovskite solar cells (PSCs) have emerged as one of the most promising candidates for next-generation photovoltaic technology, achieving impressive power conversion efficiencies of more than 26 %. However, their widespread application is hindered by issues related to instability under real-world conditions, primarily due to moisture, heat, and irradiation. One effective strategy to mitigate these challenges is the use of polymer encapsulation layers, which protect the cells from environmental degradation. However, the optimal design of these encapsulation layers remains largely unexplored, with most current approaches relying on trial-and-error experimentation.

This research aims to leverage machine learning (ML) techniques to optimize the structure of polymer encapsulation layers for PSCs, improving their stability under accelerated aging conditions. By analyzing data from existing studies on polymer properties and their impact on PSC performance, we will develop a supervised ML model to identify key polymer features that enhance stability. The project will involve collaboration between K. N. Toosi University of Technology and ZHAW University, combining the visiting researcher's expertise in ML with the host institution's advanced experimental capabilities.

Through this project, we aim to create a roadmap for designing highly stable PSCs, demonstrating a substantial improvement in device lifetime and efficiency over traditional experimental methods.

We expect that our research will open up new approaches for practical application of PSCs by solving their instability under real operation conditions.

The project will also foster long-term collaborations and knowledge exchange between the participating institutions, contributing to the advancement of energy and environmental science.