astro-ph.HEApr 28, 2026

Learning Neural Operator Surrogates for the Black Hole Accretion Code

Authors: Matthias Nägele, Cedric Bös, Chester Tan, Christian M. Fromm, Ingo Scholtes, Karl Mannheim

Organizations: Institute for Theoretical Physics and Astrophysics, Julius-Maximilians-Universität Würzburg, Würzburg, Germany · Chair for Machine Learning for Complex Networks, Julius-Maximilians-Universität Würzburg, Würzburg, Germany

Abstract

General-relativistic magnetohydrodynamic (GR-MHD) simulations are essential for studying black hole accretion, relativistic jets, and magnetic reconnection, yet their computational cost severely limits systematic parameter exploration. We investigate neural operator surrogates for two astrophysically relevant simulation scenarios produced by the Black Hole Accretion Code (\texttt{BHAC}). First, a Physics Informed Fourier Neural Operator (PINO) is trained on the special-relativistic resistive MHD (SRRMHD) evolution of the Orszag-Tang vortex over a range of resistivities spanning the Sweet-Parker and fast reconnection regimes. By embedding the governing equations as an additional loss term evaluated at finer temporal resolution than the available data supervision, the model learns dynamics at time steps where no simulation data is provided, enabling recovery of plasmoid formation that a data-only baseline trained on the same sparse snapshots fails to reproduce. To our knowledge, the present work is the first application of a physics informed neural operator to special relativistic resistive MHD, and the first to investigate the capability of such models to resolve plasmoid formation in SRRMHD. In a second line of investigation, an OFormer-style Transformer Neural Operator is trained on the evolution of spine-sheath relativistic jets created with \texttt{BHAC}, in special-relativistic MHD (SRMHD). The model is directly applied on the adaptive mesh, highlighting the need for linear attention due to long sequences. The neural surrogate model is capable of capturing most of the major details, especially in early predictions. To our knowledge, this constitutes the first application of a neural operator directly on a high resolution adaptive mesh refinement grid in the context of MHD simulations.

Explore similar work

CardsList
May 27, 2026cs.LG

Sequential Physics-Constrained Neural Operator Forward Modeling for the \textit{Norne} Reservoir System

We develop a comprehensive mathematical and computational framework for sequential surrogate modeling of three-phase black-oil reservoir dynamics using neural operators, with particular emphasis on Fourier Neural Operators (FNO) and their physics-informed variant (PINO). The application focus is the Norne benchmark reservoir, defined on a heterogeneous 46×112×2246\times112\times22 grid (N=113,344N=113,344 cells), with a production history spanning T=30T=30 timesteps covering 3298 days. Our theoretical contributions are organized around four interlocking problems: (1) functional-analytic formulation in a product-Sobolev-space setting, including well-posedness of the implicit timestep map and sharp local Lipschitz estimates; (2) covariate shift quantification, proving that the Wasserstein-2 distance grows as W2≤ε(Ln−1)/(L−1)W_2 \leq \varepsilon(L^n-1)/(L-1), with exponential population-risk discrepancy for L>1L>1; (3) physics-constrained spectral stability, showing PINO training with λR≥λR∗λ_R \geq λ^*_R reduces the learned Jacobian spectral radius to ρF+CλR−1/2ρ_F + Cλ_R^{-1/2}, yielding uniform-in-time rollout error ∣δn∣≤ε/(1−ρ)|δ_n| \leq \varepsilon/(1-ρ); and (4) KK-step TBPTT gradient analysis, deriving geometric bias decay O(ρK)O(ρ^K), optimal window K=O(log⁡(T/σ2))K^ = O(\log(T/σ^2)), and Adam convergence O(1/t)+O(ρK∗)O(1/\sqrt{t}) + O(ρ^{K^*}). Empirical validation confirms all theoretical predictions: autoregressive PINO surrogates sustain R2>0.99R^2>0.99 (oil), R2>0.90R^2>0.90 (gas), R2≈0.80R^2\approx 0.80 (pressure), and monotonically improving R2R^2 (water) across the full 3298-day horizon, trained on eight NVIDIA B200 GPUs in under one hour. A 1000-member ensemble runs in under one minute on a single B200 GPU, giving a ∼104×{\sim}10^4\times wall-clock speedup over the OPM finite-volume simulator.
Clement Etienam, Juntao Yang, Oleg Ovcharenko +4
Fourier Neural OperatorsNeural OperatorsSurrogate ModelsReservoirConventional Physics-Informed Neural NetworksSequential
AskPDF
Jun 13, 2026cs.LG

Towards Data-Efficient Cross-Device Generalization of Grad-Shafranov Equilibria via Transfer Learning Neural Operator

Real-time reconstruction of magnetohydrodynamic equilibria is essential for plasma shaping, stability assessment and feedback control in magnetic confinement fusion. However, Grad-Shafranov equilibrium calculations remain largely device-specific and iterative, limiting their use in latency-constrained control settings. Existing neural approaches can accelerate individual equilibrium predictions, but they do not generally provide reusable models across changing plasma boundaries or tokamak geometries. Here we show that equilibrium reconstruction can be recast as a cross-device operator learning problem. We develop a domain-specific neural operator framework that maps geometry and profile parameters directly to the poloidal flux field, replacing repeated solve-on-demand computation with amortized operator inference. Using the analytically tractable Solov'ev family as a controlled Grad-Shafranov testbed, we generate equilibria across eight geometrically distinct tokamak-like configurations and benchmark five neural operator architectures under four transfer-learning strategies. Single-geometry pretraining gives poor transfer to unseen devices, whereas multi-geometry pretraining enables data-efficient adaptation. The Wavelet Neural Operator gives the strongest cross-geometry performance, reaching mean relative L2 errors below 4% with 100 labelled target equilibria and below 2% with full fine-tuning. The predicted magnetic fields satisfy the divergence-free constraint to numerical precision, and four architectures achieve millisecond or sub-millisecond inference. These results identify neural operator pretraining as a route towards reusable, real-time equilibrium inference across fusion device configurations.
Jay Phil Yoo, William Howes, Yashika Ghai +3
Plasma Shape ControlNeural OperatorsEquilibrium
AskPDF
Jun 15, 2026cs.LG

PhysGuard: Fisher-Guided Gradient Projection for Sim-to-Real Neural PDE Surrogates

Neural operator models trained on simulation data often lose accuracy when applied to experimental measurements due to the sim-to-real gap. Standard fine-tuning with limited real data can reduce this gap, but it may also damage the core physics-relevant representations learned during pretraining. Although knowledge-preserving adaptation has been widely investigated in vision or language tasks, it remains unclear whether these methods are suitable for neural operators whose architectures and protected knowledge are fundamentally different. Neural operators need to preserve core-scale physical structures rather than semantic or visual features. We propose PhysGuard, a physics-preserving framework for accurate sim-to-real adaptation of neural operators. Specifically, PhysGuard uses the empirical Fisher Information Matrix computed on simulation data to identify physics-critical parameter directions, then restricts fine-tuning updates to directions that do not interfere with them. A layer-wise Gram-matrix formulation makes this efficient for models with millions of parameters, while an adaptive threshold automatically determines the protected subspace size. A spectral probe experiment shows that the dominant Fisher directions are strongly associated with low-frequency output structures. Experiments on benchmark across four neural operator architectures and different physical systems show that PhysGuard performs strongly on most evaluation metrics compared to baselines. The benefits are most evident under severe domain shift, where it reduces low-frequency error by up to 32% compared to standard fine-tuning while maintaining adaptability. Our code is available at https://github.com/ZhouChaunge/PhysGuard.
Changjian Zhou, Junfeng Fang, Negin Yousefpour +3
Neural OperatorsConventional Physics-Informed Neural NetworksFisher InformationSim-To-Real Gap
AskPDF