Saved in:
Bibliographic Details
Main Authors: Kacmaz, Semih, Huerta, E. A., Haas, Roland
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.02106
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915737272057856
author Kacmaz, Semih
Huerta, E. A.
Haas, Roland
author_facet Kacmaz, Semih
Huerta, E. A.
Haas, Roland
contents We present a hybrid machine learning framework that combines Physics-Informed Neural Operators (PINOs) with score-based generative diffusion models to simulate the full spatio-temporal evolution of two-dimensional, incompressible, resistive magnetohydrodynamic (MHD) turbulence across a broad range of Reynolds numbers ($\mathrm{Re}$). The framework leverages the equation-constrained generalization capabilities of PINOs to predict coherent, low-frequency dynamics, while a conditional diffusion model stochastically corrects high-frequency residuals, enabling accurate modeling of fully developed turbulence. Trained on a comprehensive ensemble of high-fidelity simulations with $\mathrm{Re} \in \{100, 250, 500, 750, 1000, 3000, 10000\}$, the approach achieves state-of-the-art accuracy in regimes previously inaccessible to deterministic surrogates. At $\mathrm{Re}=1000$ and $3000$, the model faithfully reconstructs the full spectral energy distributions of both velocity and magnetic fields late into the simulation, capturing non-Gaussian statistics, intermittent structures, and cross-field correlations with high fidelity. At extreme turbulence levels ($\mathrm{Re}=10000$), it remains the first surrogate capable of recovering the high-wavenumber evolution of the magnetic field, preserving large-scale morphology and enabling statistically meaningful predictions.
format Preprint
id arxiv_https___arxiv_org_abs_2507_02106
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Resolving Turbulent Magnetohydrodynamics: A Hybrid Operator-Diffusion Framework
Kacmaz, Semih
Huerta, E. A.
Haas, Roland
Fluid Dynamics
Artificial Intelligence
Machine Learning
General Relativity and Quantum Cosmology
Computational Physics
J.2; I.2
We present a hybrid machine learning framework that combines Physics-Informed Neural Operators (PINOs) with score-based generative diffusion models to simulate the full spatio-temporal evolution of two-dimensional, incompressible, resistive magnetohydrodynamic (MHD) turbulence across a broad range of Reynolds numbers ($\mathrm{Re}$). The framework leverages the equation-constrained generalization capabilities of PINOs to predict coherent, low-frequency dynamics, while a conditional diffusion model stochastically corrects high-frequency residuals, enabling accurate modeling of fully developed turbulence. Trained on a comprehensive ensemble of high-fidelity simulations with $\mathrm{Re} \in \{100, 250, 500, 750, 1000, 3000, 10000\}$, the approach achieves state-of-the-art accuracy in regimes previously inaccessible to deterministic surrogates. At $\mathrm{Re}=1000$ and $3000$, the model faithfully reconstructs the full spectral energy distributions of both velocity and magnetic fields late into the simulation, capturing non-Gaussian statistics, intermittent structures, and cross-field correlations with high fidelity. At extreme turbulence levels ($\mathrm{Re}=10000$), it remains the first surrogate capable of recovering the high-wavenumber evolution of the magnetic field, preserving large-scale morphology and enabling statistically meaningful predictions.
title Resolving Turbulent Magnetohydrodynamics: A Hybrid Operator-Diffusion Framework
topic Fluid Dynamics
Artificial Intelligence
Machine Learning
General Relativity and Quantum Cosmology
Computational Physics
J.2; I.2
url https://arxiv.org/abs/2507.02106