mlsanityData to 14 Oct 2026

Learning Neural Operator Surrogates for the Black Hole Accretion Code

arXiv 2604.25985 ↗First posted 28 Apr 2026astro-ph.HE cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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 (textttBHAC). 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 textttBHAC, 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 57 references that are in the map. First posted on arXiv 28 Apr 2026.

Builds on

30 of 57 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2016Layer Normalizationcited by 5,669
  5. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  6. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  7. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  8. 2019Root Mean Square Layer Normalizationcited by 1,480
  9. 2020Neural Operator: Graph Kernel Network for Partial Differential Equationscited by 734
  10. 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 527
  11. 2022Fourier Neural Operator with Learned Deformations for PDEs on General Geometriescited by 427
  12. 2021Neural Operator: Learning Maps Between Function Spacescited by 414
18 more
  1. 2021Choose a Transformer: Fourier or Galerkincited by 343
  2. 2024Transolver: A Fast Transformer Solver for PDEs on General Geometriescited by 326
  3. 2023Geometry-Informed Neural Operator for Large-Scale 3D PDEscited by 303
  4. 2022Transformer for Partial Differential Equations' Operator Learningcited by 283
  5. 2023Spherical Fourier Neural Operators: Learning Stable Dynamics on the Spherecited by 233
  6. 2025Transolver++: An Accurate Neural Solver for PDEs on Million-Scale Geometriescited by 97
  7. 2025Geometry Aware Operator Transformer as an Efficient and Accurate Neural Surrogate for PDEs on Arbitrary Domainscited by 62
  8. 2024Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEscited by 59
  9. 2024Continuum Attention for Neural Operatorscited by 40
  10. 2022wPINNs: Weak Physics informed neural networks for approximating entropy solutions of hyperbolic conservation lawscited by 29
  11. 2026Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale Geometriescited by 20
  12. 2025Fourier Neural Operators Explained: A Practical Perspectivecited by 16
  13. 2025Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learningcited by 12
  14. 2025Challenges and Advancements in Modeling Shock Fronts with Physics-Informed Neural Networks: A Review and Benchmarking Studycited by 11
  15. 2025Mesh-Informed Neural Operator : A Transformer Generative Approachcited by 11
  16. 2025AMR-Transformer: Enabling Efficient Long-range Interaction for Complex Neural Fluid Simulationcited by 8
  17. 2023Magnetohydrodynamics with Physics Informed Neural Operatorscited by 7
  18. 2025Resolving Turbulent Magnetohydrodynamics: A Hybrid Operator-Diffusion Frameworkcited by 4

Built on by

Not cited yet.