By continuing to browse the site, you are agreeing to our use of cookies. (More details)

THESIS - Learning for satellite Imaging : SWOT Mission

This offer is available in the following languages:
Français - Anglais

Ensure that your candidate profile is correct before applying. Your profile information will be added to the details for each application. In order to increase your visibility on our Careers Portal and allow employers to see your candidate profile, you can upload your CV to our CV library in one click!

Faites connaître cette offre !

General information

Reference : UMR5251-AGNCHE-002
Workplace : TALENCE
Date of publication : Thursday, May 21, 2020
Scientific Responsible name : Nicolas PAPADAKIS
Type of Contract : PhD Student contract / Thesis offer
Contract Period : 36 months
Start date of the thesis : 1 October 2020
Proportion of work : Full time
Remuneration : 2 135,00 € gross monthly

Description of the thesis topic

The main objective of this PhD project is to propose efficient automatic tools for processing the raw data provided by the next SWOT (Surface Water and Ocean Topography, NASA/CNES) satellite from 2021. A mathematical modelling study will be necessary to deal with data noise and analyze the different scales of the underlying physical dynamic. In practice, machine learning approaches will be considered as they offer an efficient methodology for tackling the denoising problem. In order to propose flexible architecture, multi-task learning frameworks will be considered. This will namely include applications such as image denoising, image inpainting or the separation of physical scales of the observed dynamic. The fallout of these work will concern different scientific aspects: (i) Better understanding of submesoscale processes in ocean dynamics; (ii) Improvement of numerical weather prediction systems; and (iii) Development of responsible numerical tools, able to compress relevant satellite information and decrease the quantity of data unnecessarily transferred and stored.

Expected skills: Master degree in applied mathematics, machine learning or data science. Python programming.

Work Context

The Intitute of Mathematics of Bordeaux (IMB) is a mixed unit of research (UMR 5251) associated to CNRS, university of Bordeaux and Bordeaux INP.
The Institute of Mathematics hosts the doctoral school of mathematics and computing science. The IMB gathers most of the research activity of the 136 researchers, of the 102 phd students and post-doctorants, and of the 24 members of the staff devoted to assist research.

The thesis will take place in Bordeaux, under the superviszion of Nicolas papadakis (IMB) and Emmanuel Cosme (IGE, Grenoble). The PhD candidate will realize long stay visits in Grenoble.

We talk about it on Twitter!