Spectral Learning of Magnetized Plasma Dynamics: A Neural Operator Application
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918079306399744 |
|---|---|
| author | Duarte, Roberta Nemmen, Rodrigo Santos-Lima, Reinaldo |
| author_facet | Duarte, Roberta Nemmen, Rodrigo Santos-Lima, Reinaldo |
| contents | Fourier neural operators (FNOs) provide a mesh-independent way to learn solution operators for partial differential equations, yet their efficacy for magnetized turbulence is largely unexplored. Here we train an FNO surrogate for the 2-D Orszag-Tang vortex, a canonical non-ideal magnetohydrodynamic (MHD) benchmark, across an ensemble of viscosities and magnetic diffusivities. On unseen parameter settings the model achieves a mean-squared error of $\approx 6 \times 10^{-3}$ in velocity and $\approx 10^{-3}$ in magnetic field, reproduces energy spectra and dissipation rates within $96\%$ accuracy, and retains temporal coherence over long timescales. Spectral analysis shows accurate recovery of large- and intermediate-scale structures, with degradation at the smallest resolved scales due to Fourier-mode truncation. Relative to a UNet baseline the FNO cuts error by $97\%$, and compared with a high-order finite-volume solver it delivers a $25\times$ inference speed-up, offering a practical path to rapid parameter sweeps in MHD simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01388 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spectral Learning of Magnetized Plasma Dynamics: A Neural Operator Application Duarte, Roberta Nemmen, Rodrigo Santos-Lima, Reinaldo High Energy Astrophysical Phenomena Computational Physics Fourier neural operators (FNOs) provide a mesh-independent way to learn solution operators for partial differential equations, yet their efficacy for magnetized turbulence is largely unexplored. Here we train an FNO surrogate for the 2-D Orszag-Tang vortex, a canonical non-ideal magnetohydrodynamic (MHD) benchmark, across an ensemble of viscosities and magnetic diffusivities. On unseen parameter settings the model achieves a mean-squared error of $\approx 6 \times 10^{-3}$ in velocity and $\approx 10^{-3}$ in magnetic field, reproduces energy spectra and dissipation rates within $96\%$ accuracy, and retains temporal coherence over long timescales. Spectral analysis shows accurate recovery of large- and intermediate-scale structures, with degradation at the smallest resolved scales due to Fourier-mode truncation. Relative to a UNet baseline the FNO cuts error by $97\%$, and compared with a high-order finite-volume solver it delivers a $25\times$ inference speed-up, offering a practical path to rapid parameter sweeps in MHD simulations. |
| title | Spectral Learning of Magnetized Plasma Dynamics: A Neural Operator Application |
| topic | High Energy Astrophysical Phenomena Computational Physics |
| url | https://arxiv.org/abs/2507.01388 |