Machine Learning Enhanced High‐Throughput Fabrication and Optimization of Quasi‐2D Ruddlesden–Popper Perovskite Solar Cells (Adv. Energy Mater. 38/2023)

摘要

Perovskite Solar Cells In article number 2203859, Nastaran Meftahi, Maciej Adam Surmiak, Andrew J. Christofferson, and co-workers present a methodology for efficiently exploring the vast compositional space of quasi-2D Ruddlesden-Popper perovskite solar cells using a combination of machine learning and a reproducible, combinatorial high-throughput robotic fabrication process. This methodology provides a platform for further optimization of solar cell power conversion efficiency and stability.