Said Ouala

Recherche

Said Ouala is a member of the multidisciplinary Odyssey (Ocean DYnamicS obSErvation analYsis) at INRIA, specializing in the analysis of ocean dynamics and observational data. His research focuses on improving Earth system modeling components using artificial intelligence techniques. Specifically, he works on :

• The development of new Earth system observational products.
• The design of new data assimilation techniques.
• The development of predictive models that combine physical knowledge with machine learning.

He recently explored the possibility of combining geophysical models with machine learning components to develop hybrid models trained directly from observational data^[1]. The tools and models developed in his research aim to better characterize extreme events in the ocean, atmosphere, and climate, which in turn would improve short-term forecasting and statistical modeling of these events.
 

Teaching

Said Ouala is also involved in teaching engineering students at IMT Atlantique, where he contributes to teaching probability and statistics for first-year engineering students. He also participates in the Master’s program in Data Science and Oceanography at the European Institute for Marine Studies, where he gives a lecture on data assimilation.

Background

Said Ouala graduated from the École Nationale Polytechnique of Algeria in 2015, he then obtained a Master’s degree in Artificial Intelligence from Sorbonne University in 2017. He pursued a Ph.D. in Artificial Intelligence and Geophysical Data Assimilation at IMT Atlantique, from which he graduated in 2021.
After his Ph.D., he became a Research Associate in the European ERC STUOD (Stochastic Transport in Upper Ocean Dynamics) project, within INRIA’s Odyssey team.
 

_{[1] Ouala, S., Chapron, B., Collard, F., Gaultier, L., & Fablet, R. (2024). Online calibration of deep learning sub-models for hybrid numerical modeling systems. Communications Physics, 7(1), 402.}