Michael Abdelmalik (TU/e) together with Jonathan Citrin (DIFFER+TU/e) and Barry Koren (TU/e) will receive a grant for two PhD students from the EAISI EMDAIR program. The grant stimulates exploratory multidisciplinary AI (Artificial Intelligence) research.
Understanding plasma instability
The motivation for the research lies in the fact that current fusion for energy experiments exhibit plasma instabilities that must be fully understood and controlled for viable reactor operation. These instabilities, driven by strong gradients in plasma pressure, can cause leakage of plasma energy and must be mitigated to avoid wearing out internal components in the fusion reactor.
AI to accelerate computation time
A fully accurate description of plasma instabilities demand for computationally expensive models that run on super computers. New AI techniques aim to significantly accelerate the computation time of these expensive models in the near future. As a consequence, it will make more accurate physics calculations more routinely available to researchers.
The official name of the research is: Neural Green’s Operators (NGO) as Surrogates for Parametric Solutions of Partial Differential Equations.