General information
Reference : UMR5126-DELMAR-002
Nombre de Postes : 1
Workplace : TOULOUSE
Date of publication : Thursday, January 12, 2023
Type of Contract : FTC Technical / Administrative
Contract Period : 17 months
Expected date of employment : 1 April 2023
Proportion of work : Full time
Remuneration : 2213.87€ and 2335.41€ gross per month depending on experience
Desired level of education : 5-year university degree
Experience required : 1 to 4 years
Missions
Within the CESBIO laboratory, the incumbent will be in charge of a research study on the use of machine learning methods to improve the consideration of aerosol types in the MAJA atmospheric correction chain. The aim is to explore single and multi-variable regression approaches in order to select the most efficient one, which is the result of a compromise between simplicity and speed, accuracy and robustness. The long-term objective is to implement this method in the MAJA chain, which is notably used at CNES in the operational processing of Sentinel-2 data distributed to the community, but also to prepare the use of the chain for the future TRISHNA space mission.
Activities
The work required will consist in :
- getting to grips with the radiative transfer calculation tools and learning libraries
- developing methods and tools for generating the training set in an HPC environment
- coding and evaluate the performance of the different learning methods;
- contributing to the implementation and validation of the prototype of the selected algorithm in the MAJA chain.
Skills
The incumbent should have a strong background in computer science and mathematics, with some knowledge of data science if possible. A good knowledge of Python is essential, and a good knowledge of learning method libraries (Pytorch, scikit-learn, xarray, Pandas) would be appreciated.
Team spirit
Autonomy
Good knowledge of English
Work Context
The Centre d'Études Spatiales de la Biosphère (CESBIO) is a public research laboratory at the forefront of the field of space remote sensing. The laboratory has nevertheless maintained a human scale with a staff of around 100 people who contribute to the development of themes as varied as ecology, water resource management and agronomy using data from Earth observation satellites.
We talk about it on Twitter!