Offre en lien avec l’Action/le Réseau : – — –/– — –

Laboratoire/Entreprise : LITIS Lab, Rouen Normandie
Durée : 5 to 6 months
Contact : paul.honeine@univ-rouen.fr
Date limite de publication : 2026-01-23

Contexte :

Sujet :
The foundation model (FM) paradigm is undoubtedly a major breakthrough in Machine Learning (ML) for Artificial Intelligence (AI). An FM is a large-scale neural network pre-trained with self-supervision on a vast unannotated dataset and designed to perform downstream tasks with minimal fine-tuning on small annotated datasets. While FMs have made an outstanding leap in computer vision and large language models, they have not yet emerged in fields where data is more complex, such as hyperspectral imaging and chemical analysis. Unlike traditional cameras with their primary colors (red, green, and blue), hyperspectral cameras capture detailed spectral information at every pixel, providing a detailed description of the properties of the material in the scene. ML methods have been devised to explore hyperspectral images, mainly addressing spectral unmixing, classification, and segmentation tasks. With the FM paradigm reshaping the landscape of ML, there is growing interest in FMs for hyperspectral imaging, with several papers published very recently mainly for image segmentation in airborne or satellite images [1, 2, 3].

This internship, leading to a PhD thesis, is an integral part of the interdisciplinary project HyFoundationS (Hyperspectral Foundation Models for Chemical Soil Analysis). Led by the LITIS Lab, HyFoundationS aims to develop an FM for chemical analysis of soil pollution by hyperspectral imaging. In order to unleash the full potential of FMs in the analysis of soil pollution, HyFoundationS brings together an AI laboratory (LITIS), a chemistry laboratory (Institut CARMeN), and a startup specialized in soil pollution analysis (Tellux). This consortium has been working together for more than 5 years, developing ML and chemical analysis for soil pollution assessment using hyperspectral cameras installed on a bench in lab conditions, allowing full environmental control on a wide variety of pollutants. HyFoundationS aims to provide major innovations to overcome key scientific and technical barriers for soil pollution analysis with FMs.

The intern will work (i) on reviewing the literature of FMs for hyperspectral imaging, focusing on several recently published papers [1, 2, 3], (ii) on providing a solid local implementation of an FM, (iii) on extending it to address chemical analysis tasks, and (iv) on providing experiments and evaluation for a case study. This work will be carried out in close collaboration with post-doc fellows, engineers, and senior researchers in AI, in chemical analysis, and in geoscience.

[1] N. A. A. Braham, C. M. Albrecht, J. Mairal, J. Chanussot, et al., “SpectralEarth: Training hyperspectral foundation models at scale.” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2025).
[2] D. Wang, M. Hu, Y. Jin, Y. Miao, et al., “Hypersigma: Hyperspectral intelligence comprehension foundation model.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025.
[3] D. Hong, B. Zhang, X. Li, Y. Li, C. Li, et al., “SpectralGPT: Spectral remote sensing foundation model,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024.

Profil du candidat :
We are seeking a highly motivated intern with a strong interest in AI for science. The candidate must be in a Master’s or an engineering program in computer science, applied mathematics, AI, or a related field (including remote sensing), and must have solid technical skills in deep learning, with experience in Python and the common ML libraries.

Candidates with a strong interest in interdisciplinary research and who are able to work in a collaborative environment are strongly encouraged to apply.

If interested in an internship leading to a PhD, please send your CV and transcripts along with a motivational email to paul.honeine@univ-rouen.fr.
We also welcome applications for a PhD or Post-doc within the project HyFoundationS.

Formation et compétences requises :

Adresse d’emploi :
Rouen Normandie