Machine Learning Accelerated Plasma Simulation through Physics Guided Time Jumps
Abstract
We present a machine-learning-accelerated plasma simulation scheme that combines learned time jumps with ordinary physics evolution. A neural network corrects a low-cost physics forecast over multiple time steps, while the original solver reconstructs the state and advances it between jumps through short reanchoring intervals. The scheme is implemented in PASCHEN-1D, a one-dimensional drift-diffusion-Poisson solver, achieving up to 4.70 × CPU rollout speedup relative to the ordinary solver for nanosecond pulsed nitrogen discharges. The simulations capture pre-breakdown evolution, rapid sheath formation, expansion and collapse under pulsed-voltage excitation, and post-pulse afterglow. Bulk densities and electric fields agree closely with the ordinary-solver reference, while cathode sheath width, gap voltage, and discharge current reproduce the principal temporal features. The largest spatial discrepancies occur in the cathode sheath during fast transients. A sweep of the physics-reanchoring duration reveals a trade-off between accuracy, acceleration, and numerical stability over the tested 500 ns simulation interval. A model trained on simulations with 1000 grid points also shows useful transfer to 500- and 1500-point meshes without retraining. These results demonstrate a practical route to accelerating plasma simulations by augmenting an established physics solver with machine learning.
Related
- Passage of particles through matter and the effective straggling-function: High-fidelity accelerated simulation via Physics-Informed Machine Learning
- Machine Learning Accelerated Simulation of Charge Regulation Effects
- Physics-Guided Machine Learning for Predictive Turbulent Combustion Simulation
- Missing physics discovery through fully differentiable finite element-based machine learning
- A Physics-based and Geometry-aware Reduced-order Framework for Accelerated Part-Scale Thermomechanical Simulation of Additive Friction Stir Deposition Process
BibTeX
@misc{iqbal2026machine,
title = {{Machine Learning Accelerated Plasma Simulation through Physics Guided Time Jumps}},
author = {Asif Iqbal and Peng Zhang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.23358},
eprint = {2609.23358},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.23358},
}
RIS
TY - UNPB
TI - Machine Learning Accelerated Plasma Simulation through Physics Guided Time Jumps
AU - Asif Iqbal
AU - Peng Zhang
PY - 2026
DA - 2026/09/20
PB - arXiv
DO - 10.48550/arxiv.2609.23358
UR - https://arxiv.org/abs/2609.23358
AB - We present a machine-learning-accelerated plasma simulation scheme that combines learned time jumps with ordinary physics evolution. A neural network corrects a low-cost physics forecast over multiple time steps, while the original solver reconstructs the state and advances it between jumps through short reanchoring intervals. The scheme is implemented in PASCHEN-1D, a one-dimensional drift-diffusion-Poisson solver, achieving up to 4.70 × CPU rollout speedup relative to the ordinary solver for nanosecond pulsed nitrogen discharges. The simulations capture pre-breakdown evolution, rapid sheath formation, expansion and collapse under pulsed-voltage excitation, and post-pulse afterglow. Bulk densities and electric fields agree closely with the ordinary-solver reference, while cathode sheath width, gap voltage, and discharge current reproduce the principal temporal features. The largest spatial discrepancies occur in the cathode sheath during fast transients. A sweep of the physics-reanchoring duration reveals a trade-off between accuracy, acceleration, and numerical stability over the tested 500 ns simulation interval. A model trained on simulations with 1000 grid points also shows useful transfer to 500- and 1500-point meshes without retraining. These results demonstrate a practical route to accelerating plasma simulations by augmenting an established physics solver with machine learning.
ER -