Discovering Process Dynamics for Scalable Perovskite Solar Cell Manufacturing with Explainable AI
Abstract
Large-area processing of perovskite semiconductor thin-films is complex and evokes unexplained variance in quality, posing a major hurdle for the commercialization of perovskite photovoltaics. Advances in scalable fabrication processes are currently limited to gradual and arbitrary trial-and-error procedures. While the in situ acquisition of photoluminescence (PL) videos has the potential to reveal important variations in the thin-film formation process, the high dimensionality of the data quickly surpasses the limits of human analysis. In response, this study leverages deep learning (DL) and explainable artificial intelligence (XAI) to discover relationships between sensor information acquired during the perovskite thin-film formation process and the resulting solar cell performance indicators, while rendering these relationships humanly understandable. The study further shows how gained insights can be distilled into actionable recommendations for perovskite thin-film processing, advancing toward industrial-scale solar cell manufacturing. This study demonstrates that XAI methods will play a critical role in accelerating energy materials science. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000648553Publication status
publishedExternal links
Journal / series
Advanced MaterialsVolume
Pages / Article No.
Publisher
Wiley-VCHSubject
deep learning; energy materials science; explainable artificial intelligence (XAI); knowledge discovery; perovskite solar cellsOrganisational unit
03659 - Buhmann, Joachim M. / Buhmann, Joachim M.
03659 - Buhmann, Joachim M. / Buhmann, Joachim M.
03659 - Buhmann, Joachim M. / Buhmann, Joachim M.
More
Show all metadata
ETH Bibliography
yes
Altmetrics