From Numerical Simulators of PDEs to Neural Emulators and Back

• URL: http://arxiv.org/abs/2608.24547v1
• Date: Tue, 25 Aug 2026 13:34:15 GMT
• Title: From Numerical Simulators of PDEs to Neural Emulators and Back
• Abstract summary: This thesis argues neural architectures mirror classical discretizations, their errors are amenable to the same spectral analysis, and insight flows profitably in both directions.<n>Mode-wise Fourier analysis then provides a common language in which solver errors, architectural inductive biases, and training objectives can all be read off simultaneously.
• Score: 2.9612444540570113
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Simulation is central to modern engineering and science, but the cost of numerical solvers for partial differential equations (PDEs) remains a bottleneck whenever fast or many-query evaluations are required. Neural emulators trained on solver-generated data promise significant speedups, yet they are usually framed as opaque alternatives to the very methods that produce their training signal. This thesis argues the two paradigms are more alike than different: neural architectures mirror classical discretizations, their errors are amenable to the same spectral analysis, and insight flows profitably in both directions. We approach the relationship by disentangling the multiple roles a solver plays in the emulator learning pipeline. Mode-wise Fourier analysis then provides a common language in which solver errors, architectural inductive biases, and training objectives can all be read off simultaneously. Taken together, this allows synthesizing three contributions. (1) APEBench, a comprehensive benchmarking suite for autoregressive neural emulators of PDEs that uses fast differentiable pseudo-spectral solvers in JAX. (2) Progressively Refined Differentiable Physics, an investigation of the effect of unconverged solvers on surrogate training. (3) Neural Emulator Superiority, an analysis of the influence of numerical errors and architectural inductive biases.

Related papers

• Learning Metamaterial Eigenmodes with Wavelet-Encoded Fourier Neural Operators [57.64362886310329]
  We show that a machine learning surrogate based on neural operators can learn and predict multiple eigenmodes of the elastic wave equation.<n>For metamaterial design, the resulting surrogate accelerates the simulation stage of the design cycle by three orders of magnitude relative to finite element analysis on a consumer-grade CPU.<n>These results also carry broader implications for designing input encodings in other multi-mode PDE solvers based on spectral neural operators.
  arXiv  Detail & Related papers  (2026-09-08T01:21:46Z)
• INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers [61.84396402100827]
  We propose the Indirect Neural Corrector ($mathrmINC$), which integrates learned corrections into the governing equations.<n>$mathrmINC$ reduces the error amplification on the order of $t-1 + L$, where $t$ is the timestep and $L$ the Lipschitz constant.<n>We test $mathrmINC$ in extensive benchmarks, covering numerous differentiable solvers, neural backbones, and test cases ranging from a 1D chaotic system to 3D turbulence.
  arXiv  Detail & Related papers  (2025-11-16T20:14:28Z)
• Neural Emulator Superiority: When Machine Learning for PDEs Surpasses its Training Data [28.57551605623958]
  We show neural networks trained purely on low-fidelity solver data can achieve higher accuracy than those solvers when evaluated against a higher-fidelity reference.<n>We empirically validate this finding across different PDEs using standard neural architectures.<n>This work prompts a re-evaluation of emulator benchmarking, suggesting neural emulators might achieve greater physical fidelity than their training source within specific operational regimes.
  arXiv  Detail & Related papers  (2025-10-27T08:31:55Z)
• Enabling Automatic Differentiation with Mollified Graph Neural Operators [73.52999622724101]
  We propose the mollified graph neural operator ($m$GNO), the first method to leverage automatic differentiation and compute exact gradients on arbitrary geometries.<n>For a PDE example on regular grids, $m$GNO paired with autograd reduced the L2 relative data error by 20x compared to finite differences.<n>It can also solve PDEs on unstructured point clouds seamlessly, using physics losses only, at resolutions vastly lower than those needed for finite differences to be accurate enough.
  arXiv  Detail & Related papers  (2025-04-11T06:16:30Z)
• APEBench: A Benchmark for Autoregressive Neural Emulators of PDEs [22.03564074712183]
  APEBench is a benchmark suite to evaluate autoregressive neural emulators for solving partial differential equations. APEBench is based on JAX and provides a seamlessly integrated differentiable simulation framework. We propose a novel taxonomy for unrolled training and introduce a unique identifier for PDE dynamics.
  arXiv  Detail & Related papers  (2024-10-31T19:51:36Z)
• PICL: Physics Informed Contrastive Learning for Partial Differential Equations [7.136205674624813]
  We develop a novel contrastive pretraining framework that improves neural operator generalization across multiple governing equations simultaneously. A combination of physics-informed system evolution and latent-space model output are anchored to input data and used in our distance function. We find that physics-informed contrastive pretraining improves accuracy for the Fourier Neural Operator in fixed-future and autoregressive rollout tasks for the 1D and 2D Heat, Burgers', and linear advection equations.
  arXiv  Detail & Related papers  (2024-01-29T17:32:22Z)
• NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition [67.46012350241969]
  This paper proposes a general acceleration methodology called NeuralStagger. It decomposing the original learning tasks into several coarser-resolution subtasks. We demonstrate the successful application of NeuralStagger on 2D and 3D fluid dynamics simulations.
  arXiv  Detail & Related papers  (2023-02-20T19:36:52Z)
• Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics [77.34726150561087]
  Recent developments in artificial neural networks, particularly deep learning (DL), are reviewed in detail. Both hybrid and pure machine learning (ML) methods are discussed. History and limitations of AI are recounted and discussed, with particular attention at pointing out misstatements or misconceptions of the classics.
  arXiv  Detail & Related papers  (2022-12-18T02:03:00Z)
• Learning to correct spectral methods for simulating turbulent flows [6.110864131646294]
  We show that a hybrid of classical numerical techniques and machine learning can offer significant improvements over either approach alone. Specifically, we develop ML-augmented spectral solvers for three common partial differential equations of fluid dynamics.
  arXiv  Detail & Related papers  (2022-07-01T17:13:28Z)
• Self-learning Emulators and Eigenvector Continuation [0.0]
  We focus on solving a system of constraint equations efficiently using a new machine learning approach that we call self-learning emulation. A self-learning emulator is an active learning protocol that can rapidly solve a system of equations over some range of control parameters. We envision future applications of self-learning emulators for solving systems of algebraic equations, linear and nonlinear differential equations, and linear and nonlinear eigenvalue problems.
  arXiv  Detail & Related papers  (2021-07-28T16:00:47Z)
• PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics [89.81550748680245]
  We introduce a new differentiable physics benchmark called PasticineLab. In each task, the agent uses manipulators to deform the plasticine into the desired configuration. We evaluate several existing reinforcement learning (RL) methods and gradient-based methods on this benchmark.
  arXiv  Detail & Related papers  (2021-04-07T17:59:23Z)
• Large-scale Neural Solvers for Partial Differential Equations [48.7576911714538]
  Solving partial differential equations (PDE) is an indispensable part of many branches of science as many processes can be modelled in terms of PDEs. Recent numerical solvers require manual discretization of the underlying equation as well as sophisticated, tailored code for distributed computing. We examine the applicability of continuous, mesh-free neural solvers for partial differential equations, physics-informed neural networks (PINNs) We discuss the accuracy of GatedPINN with respect to analytical solutions -- as well as state-of-the-art numerical solvers, such as spectral solvers.
  arXiv  Detail & Related papers  (2020-09-08T13:26:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.