Physics-Informed Neural Networks with Architectural Physics Embedding for Large-Scale Wave Field Reconstruction

• URL: http://arxiv.org/abs/2603.02231v1
• Date: Fri, 13 Feb 2026 04:28:23 GMT
• Title: Physics-Informed Neural Networks with Architectural Physics Embedding for Large-Scale Wave Field Reconstruction
• Abstract summary: Physics-informed neural networks (PINNs) integrate physical principles into machine learning models.<n>PINNs embed physical principles only in loss functions, leading to slow convergence, optimization instability, and spectral bias.<n>This work introduces architecture physics embedded (PE)-PINN, which integrates additional physical guidance directly into the neural network architecture.
• Score: 8.953088273349499
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large-scale wave field reconstruction requires precise solutions but faces challenges with computational efficiency and accuracy. The physics-based numerical methods like Finite Element Method (FEM) provide high accuracy but struggle with large-scale or high-frequency problems due to prohibitive computational costs. Pure data-driven approaches excel in speed but often lack sufficient labeled data for complex scenarios. Physics-informed neural networks (PINNs) integrate physical principles into machine learning models, offering a promising solution by bridging these gaps. However, standard PINNs embed physical principles only in loss functions, leading to slow convergence, optimization instability, and spectral bias, limiting their ability for large-scale wave field reconstruction. This work introduces architecture physics embedded (PE)-PINN, which integrates additional physical guidance directly into the neural network architecture beyond Helmholtz equations and boundary conditions in loss functions. Specifically, a new envelope transformation layer is designed to mitigate spectral bias with kernels parameterized by source properties, material interfaces, and wave physics. Experiments demonstrate that PE-PINN achieves more than 10 times speedup in convergence compared to standard PINNs and several orders of magnitude reduction in memory usage compared to FEM. This breakthrough enables high-fidelity modeling for large-scale 2D/3D electromagnetic wave reconstruction involving reflections, refractions, and diffractions in room-scale domains, readily applicable to wireless communications, sensing, room acoustics, and other fields requiring large-scale wave field analysis.

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)
• Solving the Elastic Wave Equation with Physics-Informed Neural Networks: A Robust and Critical Assessment [0.42970700836450476]
  Physics-Informed Neural Networks (PINNs) have emerged as a promising approach for solving Partial Differential Equations (PDEs)<n>We provide a robust and critical assessment of PINNs for solving the elastic wave equation in seismology.
  arXiv  Detail & Related papers  (2026-09-07T21:01:29Z)
• PILIR: Physics-Informed Local Implicit Representation [10.009790673923789]
  We introduce the Physics-Informed Local Implicit Representation (PILIR)<n>Our approach separates the global physical domain into a discrete latent feature space and a continuous generative decoder.<n>A generative neural operator then synthesizes these local latent features into continuous physical fields, allowing accurate reconstruction of fine-scale structures.
  arXiv  Detail & Related papers  (2026-05-01T04:07:39Z)
• Scale-PINN: Learning Efficient Physics-Informed Neural Networks Through Sequential Correction [33.84065974605524]
  Physics-informed neural networks (PINNs) have emerged as a promising mesh-free paradigm for solving partial differential equations.<n>We introduce the Sequential Correction Algorithm for Learning Efficient PINN (Scale-PINN), a learning strategy that bridges modern physics-informed learning with numerical algorithms.
  arXiv  Detail & Related papers  (2026-02-23T03:38:06Z)
• ASPEN: An Adaptive Spectral Physics-Enabled Network for Ginzburg-Landau Dynamics [0.0]
  Physics-Informed Neural Networks (PINs) have emerged as a powerful, mesh-free paradigm for solving partial differential equations (PDEs)<n>They notoriously struggle with stiff, multi-scale, and nonlinear systems due to the inherent spectral bias of standard multilayer perceptron (MLP) architectures.<n>We introduce the Adaptive Spectral-Enabled Network (ASPEN), a novel architecture designed to overcome this limitation.
  arXiv  Detail & Related papers  (2025-12-02T22:58:06Z)
• PEGNet: A Physics-Embedded Graph Network for Long-Term Stable Multiphysics Simulation [8.95344024479836]
  Physical phenomena governed by partial differential equations (PDEs) are important for scientific and engineering progress.<n>PEGNet is a physics-Embedded Graph Network that incorporates PDE-guided message passing to the redesign graph neural network architecture.<n>We show significant improvements in long-term prediction accuracy and physical consistency over existing methods.
  arXiv  Detail & Related papers  (2025-11-11T19:02:16Z)
• APRIL: Auxiliary Physically-Redundant Information in Loss - A physics-informed framework for parameter estimation with a gravitational-wave case study [0.0]
  Physics-Informed Neural Networks (PINNs) embed the partial differential equations governing the system under study directly into the training of Neural Networks.<n>We present a complementary approach by including auxiliary physically-redundant information in loss.<n>We mathematically demonstrate that these terms preserve the true physical minimum while reshaping the loss landscape.
  arXiv  Detail & Related papers  (2025-10-15T15:34:19Z)
• An effective physics-informed neural operator framework for predicting wavefields [10.94738894332709]
  We introduce a physics-informed convolutional neural operator (PICNO) to solve the Helmholtz equation efficiently.<n> PICNO takes the background wavefield corresponding to a homogeneous medium and the velocity model as input function space, generating the scattered wavefield as the output function space.<n>It allows for high-resolution reasonably accurate predictions even with limited training samples.
  arXiv  Detail & Related papers  (2025-07-22T10:22:30Z)
• OmniFluids: Physics Pre-trained Modeling of Fluid Dynamics [25.066485418709114]
  We propose OmniFluids, a pure physics pre-trained model that captures fundamental fluid dynamics laws and adapts efficiently to diverse downstream tasks.<n>We develop a training framework combining physics-only pre-training, coarse-grid operator distillation, and few-shot fine-tuning.<n>Tests show that OmniFluids outperforms state-of-the-art AI-driven methods in terms of flow field prediction and statistics.
  arXiv  Detail & Related papers  (2025-06-12T16:23:02Z)
• Bruno: Backpropagation Running Undersampled for Novel device Optimization [37.69303106863453]
  We present a bottom-up approach to train neural networks for hardware based on spiking neurons and synapses built on ferroelectric non-volatile devices (RRAM)<n>The training algorithm is then tested on a dataset with a network composed of quantized synapses based on RRAM and ferroelectric integrate-and-fire neurons.
  arXiv  Detail & Related papers  (2025-05-23T12:06:43Z)
• RadioDiff-$k^2$: Helmholtz Equation Informed Generative Diffusion Model for Multi-Path Aware Radio Map Construction [76.24833675757033]
  We propose a physics-informed generative learning approach, named RadioDiff-$k2$, for accurate and efficient multipath-aware radio map (RM) construction.<n>We show that the proposed RadioDiff-$k2$ framework achieves state-of-the-art (SOTA) performance in both image-level RM construction and localization tasks.
  arXiv  Detail & Related papers  (2025-04-22T06:28:13Z)
• DimINO: Dimension-Informed Neural Operator Learning [41.37905663176428]
  DimINO is a framework inspired by dimensional analysis.<n>It can be seamlessly integrated into existing neural operator architectures.<n>It achieves up to 76.3% performance gain on PDE datasets.
  arXiv  Detail & Related papers  (2024-10-08T10:48:50Z)
• Physics-embedded Fourier Neural Network for Partial Differential Equations [35.41134465442465]
  We introduce Physics-embedded Fourier Neural Networks (PeFNN) with flexible and explainable error. PeFNN is designed to enforce momentum conservation and yields interpretable nonlinear expressions. We demonstrate its outstanding performance for challenging real-world applications such as large-scale flood simulations.
  arXiv  Detail & Related papers  (2024-07-15T18:30:39Z)
• 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)

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.