This workshop is organized in the framework of the GDRs "Défis théoriques pour le Climat” and LEFE/MANU program aims to review and discuss advances and challenges in AI/learning-based frameworks for Ocean-Atmosphere-Climate Science. Broadly speaking, the availability of large amounts of simulation and observation data and the emergence of artificial intelligence technologies (big data architectures, GPUs, prolific learning) open up new opportunities to explore open questions in ocean, atmospheric and climate sciences through a data-centric paradigm, rather than a "classical" physical paradigm, one of the central scientific challenges being precisely the ability to unify these two paradigms. The workshop will gather experts in applied math, AI and geoscience to explore, review, discuss and advance these challenges.
The specific topics of interest are:
AI for earth system model calibration
AI for climate data post-processing
AI for model discovery
AI for earth observations
The program will combine oral sessions and poster sessions in the afternoon and working groups sessions in the morning. Participants have the opportunity to present their research work as well as to propose themes of interest for working group sessions. We envision workings groups with emphasis on specific processes and/or earth system components as well as working groups with method-oriented interests.
You can register here. The registration deadline is on March 31st, 2023. There is no registration fee. When completing your registration, you can submit a communication as well as a theme for working group sessions.
Organization:
The workshop will be an hybrid event with an in-person meeting in Brest (PNBI building on Plouzane campus, see google map) and the possibility for remote participation (zoom session). There is no registration fee.
List of keynote speakers:
Tom Beucler, UNIL, Lausanne, Switzerland
Marine Demangeot, Université Montpellier, IMAG, Montpellier, France
Katherine Haynes, CSU, Fort Collins, USA
Pedram Hassanzadeh, Rice Univ., Houston, USA
Laure Raynaud, Meteo France, CNRM, Toulouse, France
Romain Roehrig, Meteo France, CNRM, Toulouse, France
Tutorials and working groups:
Tutorials:
Diffusion models and inverse problems (F. Rousseau)
Neural implicit representations (JE Jhonson)
Working groups:
Neural closures (F. Bouchet, F. Sévellec)
Uncertainty Quantification and Extremes (P. Naveau, M. Demangeot)
End-to-end deep emulators (F. Rousseau, L. Raynaud, E. Martinez)
Neural data assimilation (R. Fablet, J. Brajard, M. Beauchamp)
Scientific and organizing committee:
S. Ayata, SU, LOCEAN, Paris, France
F. Bouchet, CNRS, IPSL/LMD, Paris, France
J. Brajard, NERSC, Bergen, Norway
R. Fablet, IMT Atlantique, Lab-STICC-Odyssey, Brest, France