Learned Surrogates of Three-Dimensional Magnetohydrodynamic Turbulence
Abstract
Three-dimensional magnetohydrodynamic (MHD) turbulence, the flow of astrophysical and fusion plasmas, is costly to simulate. We present, to our knowledge, the first learned surrogates of three-dimensional resistive MHD turbulence, and compare three standard backbones in that role: a convolutional UNet, a shifted-window transformer and a Fourier neural operator. They are trained as autoregressive emulators of decaying MHD turbulence at a resolution of 1283 and Reynolds numbers of 1000, 3000 and 6000, on 500 simulations per Reynolds number, each with one two-stage procedure, single steps and then short rollouts, and stopped by one rule. Over a window of about one large-eddy turnover time, the UNet and the transformer reach relative velocity errors of 0.018 to 0.053 and keep the current sheets, the enstrophy, the current density and the energy spectra of the simulation; which of the two is the more accurate depends on the Reynolds number, the UNet leading at 3000 and 6000 and the transformer at 1000. Applied with the same backbones and training procedure to two public benchmarks, the models reach the lowest error reported to date on the isotropic turbulence set of FactFormer, 39% below the best published model. On the compressible MHD set of The Well, their rollout errors are a third to a half below those of the best of The Well's baselines. They also match a 1.3 B-parameter pretrained foundation model in its rollout windows, with 20-62 times fewer parameters. The code, the configuration of every model, the evaluation scripts and the data generator with the seed of every simulation will be released upon publication.
Related
- Three-dimensional Magnetohydrodynamic Shocks and Associated Plasma Heating in the Solar Atmosphere
- Three-dimensional Radiative-magnetohydrodynamic Modeling of Particle-beam Heating of the Solar Atmosphere
- Pair-exchange dynamics of magnetohydrodynamic turbulence
- Effects of Alfvénicity on the Compressible Energy Cascade in Magnetohydrodynamic Solar Wind Turbulence: Evidence from Parker Solar Probe, Solar Orbiter, and WIND observations
- Sub-sonic compressible magnetohydrodynamic turbulence I. Alfvénic and fast-magnetosonic injection, amplitude dependence, and compressibility effects
BibTeX
@misc{kacmaz2026learned,
title = {{Learned Surrogates of Three-Dimensional Magnetohydrodynamic Turbulence}},
author = {Semih Kacmaz and E. A. Huerta},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.01356},
eprint = {2611.01356},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01356},
}
RIS
TY - UNPB
TI - Learned Surrogates of Three-Dimensional Magnetohydrodynamic Turbulence
AU - Semih Kacmaz
AU - E. A. Huerta
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.01356
UR - https://arxiv.org/abs/2611.01356
AB - Three-dimensional magnetohydrodynamic (MHD) turbulence, the flow of astrophysical and fusion plasmas, is costly to simulate. We present, to our knowledge, the first learned surrogates of three-dimensional resistive MHD turbulence, and compare three standard backbones in that role: a convolutional UNet, a shifted-window transformer and a Fourier neural operator. They are trained as autoregressive emulators of decaying MHD turbulence at a resolution of 128^3 and Reynolds numbers of 1000, 3000 and 6000, on 500 simulations per Reynolds number, each with one two-stage procedure, single steps and then short rollouts, and stopped by one rule. Over a window of about one large-eddy turnover time, the UNet and the transformer reach relative velocity errors of 0.018 to 0.053 and keep the current sheets, the enstrophy, the current density and the energy spectra of the simulation; which of the two is the more accurate depends on the Reynolds number, the UNet leading at 3000 and 6000 and the transformer at 1000. Applied with the same backbones and training procedure to two public benchmarks, the models reach the lowest error reported to date on the isotropic turbulence set of FactFormer, 39% below the best published model. On the compressible MHD set of The Well, their rollout errors are a third to a half below those of the best of The Well's baselines. They also match a 1.3 B-parameter pretrained foundation model in its rollout windows, with 20-62 times fewer parameters. The code, the configuration of every model, the evaluation scripts and the data generator with the seed of every simulation will be released upon publication.
ER -