Chercheur scientifique en Intelligence Artificielle appliquée à la modélisation de la Biogéochimie Marine F/H
Description
As a public weather and climate expert, Météo-France is at your side to contribute to your day-to-day safety and help you make the best decisions in a changing climate. Faced with dangerous weather episodes that are even more intense and more frequent as a result of climate change, our missions in the service of your safety are crucial. We mobilize our expertise and our scientific and technological excellence to help you anticipate and adapt to challenging weather and climate phenomena.
Find us online: https://meteofrance.com/carte-didentite-de-meteo-france
Joining Météo France means becoming part of a multi-site organization, located in France, overseas, etc. Météo-France is organized into central and inter-regional divisions. Below is a presentation of the department you could join:
The Centre National de Recherches Météorologiques (CNRM) is the research department of Météo- France, Toulouse, France (http://www.cnrm.meteo.fr). Within the CNRM, the climate research group is responsible for the development of the CNRM Earth System Model (CNRM-ESM), which includes components dealing with atmospheric dynamics and chemistry (ARPEGE), ocean and sea ice (NEMO-GELATO), land surface and biosphere (SURFEX), and ocean biogeochemical processes (PISCES). CNRM has a long history within the climate research community, and has contributed to successive IPCC reports.
The research scientist recruited will join the Earth System Team (EST) within the CNRM climate research group. He/she will be in direct contact with the international/national team involved in AI4PEX (CNRS-IPSL, ITM).
Why join us?
Embark on a stimulating adventure in the service of all, alongside men and women committed to the daily challenges posed to our society by the weather and climate. And enjoy the following benefits: flexible working hours, RTT, telecommuting, administrative restaurant or luncheon voucher, 75% contribution to public transport, contribution to health insurance, sports and cultural associations depending on the site (climbing, gym, pottery, theater, etc.).
Other benefits await you, come and discover them!
Missions
The main task of this position is to develop an AI-based emulator for the PISCES marine biogeochemical model. This work will be carried out in close collaboration with the Institut Mines-Télécom (IMT) and will be divided into several sub-tasks:
Organizing, structuring and building a learning/training database based on available simulations carried out as part of CMIP, Global Carbon Budget;
Develop a first artificial intelligence-based emulator for ocean chlorophyll and surface carbon fluxes, which are the most important variables involved in biophysical or carbon cycle feedbacks in the CNRM-ESM;
Use other approaches based on artificial intelligence tools to explore hybrid modeling in order to replace parametrization by an artificial intelligence/deep learning-based model (e.g. radiative code, chlorophyll, stoichiometry, etc.) ;
Develop, as time permits, a differential model for PISCES in Jax or Julia.
Project concerned:
Ai4PEX (01/04/2024 - 31/03/2027) is a multidisciplinary project involving 18 European partners that aims to improve the representation of these feedbacks in MSEs, thereby reducing uncertainty in global warming projections. We propose a multidisciplinary approach focused on “learning” the precise description of the processes underlying these feedbacks, by merging observations with machine learning and artificial intelligence. These data and approaches, constrained by the laws of physics, will significantly improve the accuracy of Earth system models.
Specific information:
Position open to people with disabilities
Office hours
2-year fixed-term contract
Application deadline: 10/12/2024
Profil
PhD-level training is desirable, as well as experience in climate research and/or ocean science and modeling.
To fill this position, you will need the following skills:
You are familiar with the use of complex models on supercomputers and with the analysis of large climate datasets;
You have good programming skills (in particular AI/deep learning);
Knowledge of Python, NCO, CDO is an advantage;
You must be fluent in English (spoken and written).
The application must include:
A Curriculum Vitae (including research experience, publications and conferences, computer skills and practice of different languages...) ;
A brief statement of research interests;
The names and contact details (e-mail address and telephone number) of three referees.