English

3D Cloud reconstruction through geospatially-aware Masked Autoencoders

Computer Vision and Pattern Recognition 2025-01-07 v1 Artificial Intelligence

Abstract

Clouds play a key role in Earth's radiation balance with complex effects that introduce large uncertainties into climate models. Real-time 3D cloud data is essential for improving climate predictions. This study leverages geostationary imagery from MSG/SEVIRI and radar reflectivity measurements of cloud profiles from CloudSat/CPR to reconstruct 3D cloud structures. We first apply self-supervised learning (SSL) methods-Masked Autoencoders (MAE) and geospatially-aware SatMAE on unlabelled MSG images, and then fine-tune our models on matched image-profile pairs. Our approach outperforms state-of-the-art methods like U-Nets, and our geospatial encoding further improves prediction results, demonstrating the potential of SSL for cloud reconstruction.

Keywords

Cite

@article{arxiv.2501.02035,
  title  = {3D Cloud reconstruction through geospatially-aware Masked Autoencoders},
  author = {Stella Girtsou and Emiliano Diaz Salas-Porras and Lilli Freischem and Joppe Massant and Kyriaki-Margarita Bintsi and Guiseppe Castiglione and William Jones and Michael Eisinger and Emmanuel Johnson and Anna Jungbluth},
  journal= {arXiv preprint arXiv:2501.02035},
  year   = {2025}
}
R2 v1 2026-06-28T20:55:47.735Z