2025/07/02 by Kacmaz, Semih, Huerta, E. A., Haas, Roland · 1 citation
#Artificial Intelligence (cs.AI) #Computational Physics (physics.comp-ph) #FOS: Computer and information sciences #FOS: Physical sciences #Fluid Dynamics (physics.flu-dyn) #General Relativity and Quantum Cosmology (gr-qc) #I.2 #J.2 #Machine Learning (cs.LG)
paper · doi:10.48550/arxiv.2507.02106
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 (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 Re ∈ \100, 250, 500, 750, 1000, 3000, 10000\, the approach achieves state-of-the-art accuracy in regimes previously inaccessible to deterministic surrogates. At 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 (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.