A Pre-trained Variational Autoencoder for Gyrokinetic Plasma Turbulence Surrogate Modeling
physics.plasm-ph, cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- GKFieldFlow: A Spatio-Temporal Neural Surrogate for Nonlinear Gyrokinetic Turbulence
- TGLF-WINN: Data-Efficient Deep Learning Surrogate for Turbulent Transport Modeling in Fusion
- Autoregressive long-horizon prediction of plasma edge dynamics
- GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations
- Auto-Encoding Variational Bayes
Related papers
- Reconstruction of Multiscale Plasma Dynamics Across Operating Regimes
- Is Your AI Fast Enough to Run a Fusion Reactor?
- GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations
- Electromagnetic ghosts in pair plasmas
- Collisionless whistler heat-flux instability in ultra-high- beta plasmas
- On the double-adiabatic equations in the relativistic regime