En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)
Portail > Offres > Offre UMR3589-VIRGUE-006 - CDD Chercheur de 2 ans sur l'intelligence artificielle pour la paramétrisation des flux turbulents de surface en régions polaires (H/F)

2-year research position on machine learning for surface turbulent flux parameterization

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

Date Limite Candidature : mercredi 22 décembre 2021

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler. Les informations de votre profil complètent celles associées à chaque candidature. Afin d’augmenter votre visibilité sur notre Portail Emploi et ainsi permettre aux recruteurs de consulter votre profil candidat, vous avez la possibilité de déposer votre CV dans notre CVThèque en un clic !

Faites connaître cette offre !

General information

Reference : UMR3589-VIRGUE-006
Workplace : TOULOUSE
Date of publication : Wednesday, November 10, 2021
Type of Contract : FTC Scientist
Contract Period : 24 months
Expected date of employment : 17 January 2022
Proportion of work : Full time
Remuneration : between 2700 and 4000 euros monthly (before taxes), commensurate with experience
Desired level of education : PhD
Experience required : Indifferent

Missions

The Arctic sea ice has experienced a drastic decline over the last decades, perceived as an emblematic sign of climate change. Substantial reductions in sea ice cover, and also thickness, among other modifications, have already impacted largely on local ecosystems, indigenous populations and possibly lower-latitude climate. A further reduction in the sea ice cover and thus more open water exposed to the atmosphere is expected in the near future. Two to four times faster surface warming has also been observed in the Arctic than at any other latitude over the last decades. This phenomenon is commonly referred to as the Arctic amplification. Heat exchange between sea ice and atmosphere plays a crucial role on the rate of Arctic sea ice melting as well as on the teleconnections between polar and non-polar regions.

The Year of Polar Prediction (YOPP) was an extended period (2017-2019) of coordinated intensive observational and modeling activities aiming at improving polar prediction capabilities. YOPP is a WCRP/WWRP (World Climate Research Programme / World Weather Research Programme) initiative as part of the Polar Prediction Project. YOPP provided a wealth of new observations in the polar regions, that we can exploit to develop new parameterisations of the ice-atmosphere interface, in particular for latent and sensible heat fluxes.

This position is funded by the 'Make Our Planet Great Again' research program through the 5-year ASET project (Atmosphere Sea ice Exchanges and Teleconnections) focused on improving the representation of surface turbulent heat fluxes in polar regions. The research scientist will propose new parameterisations for turbulent heat fluxes based on innovative tools.

Activities

The postdoctoral research scientist will propose novel formulations for surface turbulent heat fluxes based on machine learning techniques and relying on data including both a wide dataset from previous polar experiments and observations from recent campaigns carried out within the YOPP framework. Machine-learning techniques of the regression type could be used, such as Multivariate Adaptive Regression Splines (MARS, Friedman, 1991) or Locally Estimated Scatterplot Smoothing (LOESS, Cleveland, 1981). Expertise of the candidate to select the most suitable method is very welcome. Knowledge about the physical parameters that should enter the algorithm can rely on local expertise.

Skills

1. Ph.D. in statistics for climate
2. Knowledge about machine learning
3. Programming skill : scripting and visualisation (e.g. bash, R, python)
4. Good command of English.
5. Collaborative spirit and communication skill

Work Context

The position will be held at CNRM (Centre National de Recherches Météorologiques) in Toulouse (France) in the GMGEC department (Groupe de Météorologie Grande Echelle et Climat) in the IOGA team (Interactions Océan-Glace-Atmosphère). The GMGEC department is at the forefront of climate modelling and contributes to each phase of the Coupled Model Intercomparison Project (CMIP) with its in-home coupled model, CNRM-CM, co-developed with CERFACS. The IOGA team aims at improving the representation of ocean, sea ice and atmosphere exchanges and interactions in the CNRM-CM model. IOGA contributes to the development of modelling tools used for climate predictions and projections and numerical weather predictions (for instance the SURFEX platform, used for air-ice and air-sea fluxes calculation and ocean-atmosphere coupling) and investigates coupled mechanisms and processes driving the climate system behaviour.

Constraints and risks

This projet can start anytime between January and June 2022, at the candidate convenience

We talk about it on Twitter!