Decoupling Common and Unique Representations for Multimodal Self-supervised Learning

Springer Nature Switzerland (2025) 286-303

Authors:

Yi Wang, Conrad M Albrecht, Nassim Ait Ali Braham, Chenying Liu, Zhitong Xiong, Xiao Xiang Zhu

Feature Guided Masked Autoencoder for Self-Supervised Learning in Remote Sensing

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Institute of Electrical and Electronics Engineers (IEEE) 18 (2025) 321-336

Authors:

Yi Wang, Hugo Hernández Hernández, Conrad M Albrecht, Xiao Xiang Zhu

SpectralEarth: Training Hyperspectral Foundation Models at Scale

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Institute of Electrical and Electronics Engineers (IEEE) 18 (2025) 16780-16797

Authors:

Nassim Ait Ali Braham, Conrad M Albrecht, Julien Mairal, Jocelyn Chanussot, Yi Wang, Xiao Xiang Zhu

Statistical constraints on climate model parameters using a scalable cloud-based inference framework – CORRIGENDUM

Environmental Data Science Cambridge University Press (CUP) 4 (2025)

Authors:

James Carzon, Bruno Abreu, Leighton Regayre, Kenneth Carslaw, Lucia Deaconu, Philip Stier, Hamish Gordon, Mikael Kuusela

3D Cloud reconstruction through geospatially-aware Masked Autoencoders

Workshop paper at “Machine Learning and the Physical Sciences”, NeurIPS (2024)

Authors:

Stella Girtsou, Emiliano Diaz Salas-Porras, Lilli J Freischem, Joppe Massant, Kyriaki-Margarita Bintsi, Guiseppe Castiglione, William Jones, Michael Eisinger, Emmanuel Johnson, Anna Jungbluth

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.