ML4Oceans Summer School 2026

ML4Oceans 2026 – 3rd edition!

The use of artificial intelligence is now crucial for environmental and climate issues, including oceanography. In this context, SCAI and the Institut de l'Océan of Sorbonne Université joined their forces, together with the financial support of EUR-IPSL Climate Graduate School, to offer a transdisciplinary school for PhD candidates and post-doctoral researchers. Twenty candidates will be selected according to their academic background, their research subject & their motivation to participate in this school.

The objective: to acquire knowledge and skills in AI applied to oceanography and marine ecology to analyze marine big data (imaging, satellite, floats, etc..).

Practical information

The school will take place in the seminar room of SCAI, the Sorbonne Cluster for Artificial Intelligence. It is located on the Pierre and Marie Curie Campus of Sorbonne University, 4 place Jussieu (métro Jussieu), 75005 Paris, France. Lectures will be given in English.

Important: Do not forget to bring your own laptop.

2026 Programme

The school will be from 9h to 17h or 18h, from Monday to Friday. Each day, you will have two classes of 1h30 each in the morning, by experts in their field: one on an oceanography topic and one on a machine learning topic. In the afternoon, you will have a tutored practical lab of 3h to 4h, in a dedicated computing environment, to apply a machine learning algorithm on real oceanic data. This direct application of the morning class will encompass coding, training, and applying a model.

• Monday 29th June: Introductions to the school, the programming language (Python and PyTorch) and the coding environment, with interventions from SCAI, the SU Institute of the Ocean and the EUR-IPSL. Main teacher: Jean-Olivier Irisson.
• Tuesday 30th June: Introduction to Machine Learning (ML) and Neural Networks (NN). Derivation of poorly observed variables from Argo floats. Main teachers: Anastase Charantonis, Hervé Claustre, Raphaëlle Sauzède.
• Wednesday 1st July: Convolutional Neural Network (CNN) for classification. Plankton imaging classification. Main teachers: Jérémy Fix, Jean-Olivier Irisson, Sakina-Dorothée Ayata.
• Thursday 2nd July: Detection using UNet and more complex architectures. Satellite data and eddy detection. Main teachers: Anastase Charantonis, Redouane Lguensat.
• Friday 3rd July: Physic-informed Neural Network (PINN). Marine ecosystem modelling. Main teachers: Patrick Gallinari, Redouane Lguensat, Sakina-Dorothée Ayata.

Application procedure

Please apply online before the 24th of April 2026.

Candidates will be selected using the following criteria: adequation between the school’s themes and the candidate’s research project, minimum skill requirement, motivation for the ML4Oceans school. Candidates from different backgrounds are encouraged to apply.

The outcome of the selection procedure will be communicated to the candidates early May.

Speakers

• Sakina-Dorothée Ayata, LOCEAN, SU
• Anastase Charantonis, LaMME/LOCEAN, ENSIIE/INRIA
• Hervé Claustre, LOV, SU/CNRS
• Jérémy Fix, LORIA, CentraleSupélec
• Patrick Gallinari, LIP6, SU
• Jean-Olivier Irisson, LOV, SU
• Redouane Lguensat, IPSL
• Raphaëlle Sauzède, LOV-IMEV, SU

Organising committee

• Sakina-Dorothée Ayata, LOCEAN, SU
• Anastase Charantonis, LaMME/LOCEAN, ENSIIE/INRIA
• Jérémy Fix, LORIA, CentraleSupélec
• Jean-Olivier Irisson, LOV, SU
• Redouane Lguensat, IPSL