Phd: Deep learning representations for dynamical systems: application to space oceanography

When:
01/07/2019 – 02/07/2019 all-day
2019-07-01T02:00:00+02:00
2019-07-02T02:00:00+02:00

Annonce en lien avec l’Action/le Réseau : aucun

Laboratoire/Entreprise : Lab-STICC/IMT Atlantique
Durée : 36 mois
Contact : ronan.fablet@imt-atlantique.fr
Date limite de publication : 2019-07-01

Contexte :
Artificial Intelligence (AI) technologies, models and strategies open new paradigms to address the modeling, simulation, forecasting and reconstruction of complex systems. In the context of ocean-atmosphere science, they may offer new means to exploit the potential of available observation and simulation big data. ​This PhD will aim to investigate data-driven and AI-guided strategies for complex dynamical.

Contact person: ronan fablet, ronan.fablet@imt-atlantique.fr

Sujet :
​From a methodological point of view, bridging the physical model-driven paradigm underlying ocean science and AI paradigms will at the core of this PhD with a view to developing geophysically-sound learning-based and data-driven representations of geophysical flows accounting for their key features (e.g., chaos, extremes, high-dimensionality). A key targeted application will be space oceanography for future multi-platform observing systems.

This PhD proposal involves a collaboration between Lab-STICC/IMT Atlantique (R. Fablet), Ifremer & IGE (B. Chapron, J. Le Sommer) and Univ. of Washington (S. Brunton). The PhD candidate will benefit from the gathered multidisciplinary expertise of the supervision team in Ocean Science, Ocean Remote Sensing, Fluid Dynamics, Artificial Intelligence and Control.

Additional information on our research activities at:
https://researchgate.net/profile/Ronan_Fablet

Profil du candidat :
Msc. or engineer degree in applied math, computer science, data science, signal processing and/or geoscience with a strong interest in interdisciplinary topics.

Formation et compétences requises :
Good math and computer science background
Skills in machine learning and deep learning would be highly appreciated.

Adresse d’emploi :
Principal hosting lab: Lab-STICC, IMT Atlantique
Planned stays at IGE/OceanNext (Grenoble) and Univ. of Washington (Seattle)

Document attaché :