Learn the Dynamics, Enforce the Physics: Generative Latent Operators for High-Dimensional Beam Evolution
Abstract
Particle-in-cell (PIC) simulation is indispensable for modeling beam dynamics in particle accelerators, but its computational cost limits many-query workflows, such as configuration exploration, virtual diagnostics, and controller design. We introduce GLOBE, a physics-constrained Generative Latent Operator for Beam Evolution, modeling the nonlinear, control-dependent, multiscale evolution of 3D beam--field dynamics covering 107 spatial cells. GLOBE compresses beam--field states into a compact latent space and factors their evolution into two components. A control-conditioned neural operator learns the dominant dynamics, while an amplitude-normalized generative model captures the residual distribution, recovering fine-scale structures and conditional variations. GLOBE enforces field constraints by regime-specific, parameter-free operators: a Poisson solve reconstructs the electric field in the electrostatic regime, and a spectral projection imposes Gauss's law and a divergence-free magnetic field in the electromagnetic regime. On two high-resolution 3D particle-accelerator benchmarks, bunched-beam transport and plasma-wakefield acceleration, GLOBE lowers relative-L2 error by 9\% and 13\%, low-frequency spectral error by 69\% and 51\%, and mid-frequency spectral error by 54\% and 20\% relative to the strongest baseline (DPOT), satisfies field constraints, and reduces hours of PIC simulation to a minute per rollout.
Related
- Generative Modeling of Stochastic Dynamics for Long-Time Evolution
- Smooth perturbation theory and generic Cantor spectrum for multi-dimensional monotone quasiperiodic operators
- Bi-FORK: Generative Modeling of High-Dimensional Bifurcating Systems
- PTED: A multi-dimensional two-sample test for scientific inference and generative machine learning
- Bubble nucleation with thermal higher-dimensional operators
BibTeX
@misc{zou2026learn,
title = {{Learn the Dynamics, Enforce the Physics: Generative Latent Operators for High-Dimensional Beam Evolution}},
author = {Haohan Zou and Alexander Scheinker and Yuanyuan Shi},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.14537},
eprint = {2610.14537},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.14537},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Learn the Dynamics, Enforce the Physics: Generative Latent Operators for High-Dimensional Beam Evolution
AU - Haohan Zou
AU - Alexander Scheinker
AU - Yuanyuan Shi
PY - 2026
DA - 2026/10/10
PB - arXiv
DO - 10.48550/arxiv.2610.14537
UR - https://arxiv.org/abs/2610.14537
AB - Particle-in-cell (PIC) simulation is indispensable for modeling beam dynamics in particle accelerators, but its computational cost limits many-query workflows, such as configuration exploration, virtual diagnostics, and controller design. We introduce GLOBE, a physics-constrained Generative Latent Operator for Beam Evolution, modeling the nonlinear, control-dependent, multiscale evolution of 3D beam--field dynamics covering 10^7 spatial cells. GLOBE compresses beam--field states into a compact latent space and factors their evolution into two components. A control-conditioned neural operator learns the dominant dynamics, while an amplitude-normalized generative model captures the residual distribution, recovering fine-scale structures and conditional variations. GLOBE enforces field constraints by regime-specific, parameter-free operators: a Poisson solve reconstructs the electric field in the electrostatic regime, and a spectral projection imposes Gauss's law and a divergence-free magnetic field in the electromagnetic regime. On two high-resolution 3D particle-accelerator benchmarks, bunched-beam transport and plasma-wakefield acceleration, GLOBE lowers relative-L_2 error by 9\% and 13\%, low-frequency spectral error by 69\% and 51\%, and mid-frequency spectral error by 54\% and 20\% relative to the strongest baseline (DPOT), satisfies field constraints, and reduces hours of PIC simulation to a minute per rollout.
ER -