Description

This repository contains the code associated with the paper:

Quantifying Perovskite Solar Cell Degradation via Machine Learning from Spatially Resolved Multimodal Luminescence Time Series. Giulio Barletta, Simon Ternes, Saif Ali, Zohair Abbas, Chiara Ostendi, Marialucia D’Addio, Erica Magliano, Pietro Asinari, Eliodoro Chiavazzo, Aldo Di Carlo. arXiv 2026.

LumPerNet is a deep-learning pipeline for predicting the degradation state of perovskite solar cells from spatially resolved luminescence imaging and associated JV measurements.

For further details, refer to the associated article.

Overview of the protocol for training and validating the models presented in the work.

Citation

Barletta, Giulio, et al., Quantifying Perovskite Solar Cell Degradation via Machine Learning from Spatially Resolved Multimodal Luminescence Time Series, arXiv preprint, 2026, https://doi.org/10.48550/arXiv.2603.12857.

@article{barletta2026quantifying,
  title={Quantifying Perovskite Solar Cell Degradation via Machine Learning from Spatially Resolved Multimodal Luminescence Time Series},
  author={Barletta, Giulio and Ternes, Simon and Ali, Saif and Abbas, Zohair and Ostendi, Chiara and D'Addio, Marialucia and Magliano, Erica and Asinari, Pietro and Chiavazzo, Eliodoro and Di Carlo, Aldo},
  journal={arXiv preprint arXiv:2603.12857},
  year={2026}
}