The Adaptive Solution of High-Frequency Helmholtz Equations via Multi-Grade Deep Learning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhao, Peiyao, Wang, Rui, Wu, Tingting, Xu, Yuesheng
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908850236424192
author Zhao, Peiyao
Wang, Rui
Wu, Tingting
Xu, Yuesheng
author_facet Zhao, Peiyao
Wang, Rui
Wu, Tingting
Xu, Yuesheng
contents The Helmholtz equation is fundamental to wave modeling in acoustics, electromagnetics, and seismic imaging, yet high-frequency regimes remain challenging due to the ``pollution effect''. We propose FD-MGDL, an adaptive framework integrating finite difference schemes with Multi-Grade Deep Learning to efficiently resolve high-frequency solutions. While traditional PINNs struggle with spectral bias and automatic differentiation overhead, FD-MGDL employs a progressive training strategy, incrementally adding hidden layers to refine the solution and maintain stability. Crucially, when using ReLU activation, our algorithm recasts the highly non-convex training problem into a sequence of convex subproblems. Numerical experiments in 2D and 3D with wavenumbers up to $κ=200$ show that FD-MGDL significantly outperforms single-grade and conventional neural solvers in accuracy and speed. Applied to an inhomogeneous concave velocity model, the framework accurately resolves wave focusing and caustics, surpassing the 5-point finite difference method in capturing sharp phase transitions and amplitude spikes. These results establish FD-MGDL as a robust, scalable solver for high-frequency wave equations in complex domains.
format Preprint
id arxiv_https___arxiv_org_abs_2602_20719
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Adaptive Solution of High-Frequency Helmholtz Equations via Multi-Grade Deep Learning
Zhao, Peiyao
Wang, Rui
Wu, Tingting
Xu, Yuesheng
Numerical Analysis
The Helmholtz equation is fundamental to wave modeling in acoustics, electromagnetics, and seismic imaging, yet high-frequency regimes remain challenging due to the ``pollution effect''. We propose FD-MGDL, an adaptive framework integrating finite difference schemes with Multi-Grade Deep Learning to efficiently resolve high-frequency solutions. While traditional PINNs struggle with spectral bias and automatic differentiation overhead, FD-MGDL employs a progressive training strategy, incrementally adding hidden layers to refine the solution and maintain stability. Crucially, when using ReLU activation, our algorithm recasts the highly non-convex training problem into a sequence of convex subproblems. Numerical experiments in 2D and 3D with wavenumbers up to $κ=200$ show that FD-MGDL significantly outperforms single-grade and conventional neural solvers in accuracy and speed. Applied to an inhomogeneous concave velocity model, the framework accurately resolves wave focusing and caustics, surpassing the 5-point finite difference method in capturing sharp phase transitions and amplitude spikes. These results establish FD-MGDL as a robust, scalable solver for high-frequency wave equations in complex domains.
title The Adaptive Solution of High-Frequency Helmholtz Equations via Multi-Grade Deep Learning
topic Numerical Analysis
url https://arxiv.org/abs/2602.20719