About me
I am a researcher in machine learning for Earth observation. Currently, I'm working on satellite image analysis and wildfire simulation as a postdoctoral research fellow at CNES in collaboration with the SPE lab from CNRS - Corsica University and phi-lab from ESA. My research focuses on semi/self-supervised multimodal learning and on hybrid modeling (the combination of physical models with machine learning models).I completed my PhD at ONERA, Magellium and ISAE-SUPAERO in collaboration with the Toulouse Mathematics Institute on the semantic segmentation of airborne hyperspectral images for mapping impermeable surfaces in large urban areas.
News
March 2025: For the seventh COMET TSI seminar, we were glad to welcome Emilia Arens, Johannes Dollinger and Damien Robert from the EcoVision Lab of Zurich University for a great talk about Deep Learning and Remote Sensing for Species Distribution Modeling!
January 2025: For the sixth COMET TSI seminar, we were delighted to welcome Iris Dumeur from CESBIO for a presentation about self-supervised representation learning of Satellite Image Time Series for land surface monitoring!
December 2024: For the fifth COMET TSI seminar, we were glad to have a presentation of Olin Geimer (Yale University) and Alexander Theus (ETH Zurich) about structural pruning of neural networks via optimal transport!
November 2024: For the fourth COMET TSI seminar, we had the pleasure to welcome Tobias Finn (CEREA - Ecole des Ponts Paris Tech) for a talk about sea-ice modeling with generative diffusion surrogate models!
October 2024: For the third COMET TSI seminar, we were pleased to have a presentation of Nina Maria Gottschling (DLR) about AI hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems!
May 2024: I will be at ICLR 2024 for the ML4RS workshop! [paper] [code]
November 2023: I am very glad to have successfully defended my PhD! Huge thanks to my supervisors, to Pr. Céline Hudelot and Pr. Paolo Gamba who reviewed my manuscript, and to all jury members, Yuliya Tarabalka, Karteek Alahari and Patrick Gallinari.
March 2023: I was very glad to present our research work on active learning and hybrid modeling to improve representation learning at OMP. [slides] [video]
Selected publications
|
R. Thoreau, V. Marsocci and D. Derksen Submitted to ICCV 2025. [arXiv]
|
|
R. Thoreau, L. Risser, V. Achard, B. Berthelot and X. Briottet Submitted to Springer Machine Learning. [arXiv] [code]
|
|
R. Thoreau, L. Risser, V. Achard, B. Berthelot and X. Briottet ISPRS Journal of Photogrammetry and Remote Sensing. [paper] [data set] [code] [arXiv]
|
|
R. Thoreau, V. Achard, L. Risser, B. Berthelot and X. Briottet IEEE Geoscience and Remote Sensing Magazine. [paper] [code]
|
Teaching
I'm currently giving lectures about machine learning for the MAPI3 master and the L3 FLEX (info / maths) at Paul Sabatier University.Past courses from 2020 to 2023
- Introduction to statistics (lectures) at Paul Sabatier University, 2nd year BS in Biochemistry,
- Integration and probability theory (tutorials) at ENSEEIHT engineering school,
- Statistical foundations of Machine Learning (practical works) at ISAE-SUPAERO, Data & Decision Sciences MS,
- Combinatorial optimization (practical works) at Paul Sabatier University, Computer Science MS,
- Algorithmic (practical works) at Paul Sabatier University, Computer Science BS,
- Introduction to python (practical works) at Paul Sabatier University, Civil Engineering BS.
Student supervision
- April to October 2025, Hugo André, final-year student at ISAE-SUPAERO on deep generative modeling for the inversion of industrial stack plumes from satellite images, in collaboration with Pierre-Yves Foucher (ONERA), Camille Desjardins, Laura Le Barbier and Solange Lemai-Chenevier (CNES).
- March to August 2023, Arthur Cassou, final-year student at ENSTA Bretagne on the integration of physical priors in generative models for hyperspectral data, in collaboration with Laurent Risser, Véronique Achard and Xavier Briottet.
- May to July 2022, Gaspard Loupit, second-year student at ISAE-SUPAERO on the comparison of features extracted by spatial-spectral convolutions to morphological profiles through LIME explanations for hyperspectral images, in collaboration with Véronique Achard.
- April to July 2022, Clément Lefranc, master student in computer science at Paul Sabatier University on the development of a QGIS plug-in for active learning on Earth observation data, namely AL4EO.
COMET TSI scientific seminars
The COMET Signal and Image Processing community is a community of experts initiated by CNES, the French spatial agency, in order to gather academic researchers and engineers from the space industry in France. Since May 2024, I've been organizing scientific seminars about mathematics and computing applied to Earth observation. If you would like to present your work, please reach out![Past and coming seminars]