Missions

Develop new AI tools for detecting and studying the dynamics of blobs and filaments using reflectometry experimental databases and high-fidelity fluid turbulence simulations.
Extract crucial insights such as filament frequency, velocity, and correlation time across different plasma regimes.
Estimate effective diffusion coefficients to improve predictive capabilities of mean-field codes applied in tokamak configurations.
Advance the understanding of plasma simulations in the scrape-off layer (SOL) region and their impact on plasma-wall interactions.

Activities

Conduct research on AI techniques for detecting and analyzing blobs and filaments in experimental data and simulation outputs.
Collaborate with interdisciplinary teams to develop and implement AI algorithms and tools.
Perform data analysis, interpretation, and validation of results.

Skills

The candidate will hold a PhD in mathematics, plasma physics or computer science, with a solid background in AI/machine learning techniques. A background in plasma transport phenomena as well as an experience with data analysis, statistical methods, and scientific computing will be also appreciated. The work requires also an excellent communication skills and ability to work collaboratively in a team environment.
The numerical developments required will involve team-working skills to interact frequently with other post-docs/PhD working on the same numerical code.

Work Context

The post-doc will work in an interdisciplinary team associating skills in applied mathematics, computing science and plasma physics. The M2P2 laboratory hosts the last generation of the French edge plasma codes in conjunction with IRFM-CEA where the tokamak WEST is currently operated in close connections operates with the preparation of ITER operation.