Navigate Current Projects

1. KANTEQ

A neural network framework for fast and accurate equilibrium estimation in tokamak reactors. 

2. Quasineutrality at kinetic scales

The missing kinetic picture of quasineutral plasmas

3. PHIMICON

A novel Physics-informed machine learning framework for plasma confinement

4. Hamiltonian description of kinetic, fluid-kinetic and generalized MHD models

5. Kinetic and hybrid-kinetic equilibria

6. Artificial neural networks for PDEs

7. Plasma equilibria in fusion reactors

Research Interests

My research focuses on the equilibrium, stability, and dynamics of laboratory and astrophysical plasmas, using Hamiltonian fluid dynamics, kinetic and hybrid models, as well as modern machine learning approaches. I am particularly interested in the Hamiltonian formulation of novel hybrid fluid-kinetic models that preserve fundamental conservation laws. These models have applications in the study of magnetic confinement in fusion devices such as tokamaks, as well as in astrophysical plasma phenomena like magnetic reconnection.

I also explore computational methods that inherently respect conservation laws, along with deep learning techniques, especially equation-driven machine learning and physics-informed neural networks (PINNs), to address the complex differential equations that arise in plasma physics.

Research Areas

Contributions

Further Information

More details about my work, including publications, conference presentations, and my Ph.D. thesis, are available on the following pages: Publications, Conferences, Ph.D. thesis 

You can also explore my research on my  Research Gate and  Google Scholar profiles.