Deep learning for augmented process monitoring of scalable perovskite thin-film fabrication

Scaling up perovskite solar cell manufacturing requires reliable, real-time insight into the thin-film fabrication process. This paper introduces a deep learning approach that augments in-situ process monitoring, extracting predictive signals directly from luminescence data recorded during fabrication. The resulting models help identify process irregularities early and support more robust, data-driven scale-up of perovskite photovoltaics production.

Download paper here

Recommended citation: Laufer, F., Götz, M., & Paetzold, U. W. (2025). "Deep learning for augmented process monitoring of scalable perovskite thin-film fabrication." Energy & Environmental Science.
Download Paper