Mesoscale Convective Systems in DYAMOND Models: A Feature Tracking Intercomparison.

Copernicus Publications (2025)

Authors:

Zhe Feng, Ruby Leung, Andreas Prein, Thomas Fiolleau, William Jones, Zachary Moon, Ben Maybee, Fengfei Song, Jinyan Song, Kelly Núñez Ocasio, Cornelia Klein, Adam Varble, Remy Roca, Puxi Li

3D Cloud reconstruction through geospatially-aware Masked Autoencoders

(2025)

Authors:

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

Invertible Neural Networks for Probabilistic Aerosol Optical Depth Retrieval

IEEE Transactions on Geoscience and Remote Sensing Institute of Electrical and Electronics Engineers (IEEE) 63 (2025) 1-13

Authors:

Paolo Pelucchi, Jorge Vicent Servera, Philip Stier, Gustau Camps-Valls

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.