EUVIMEDEUVIMED entdecken
Crossref

A Neural Multigrid Solver for Helmholtz Equations with High Wavenumber and Heterogeneous Media

Chen Cui, Kai Jiang, Shi Shu

SIAM Journal on Scientific Computing · 30.06.2025 · 47 (3) · C655-C679

DOI: 10.1137/24m1654397 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 15.05.2025. Verfasst von Chen Cui und 2 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Science and Technology Innovation Program of Hunan Province, Science Challenge Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we propose a deep learning–enhanced multigrid solver for high-frequency and heterogeneous Helmholtz equations. By applying spectral analysis, we categorize the iteration error into characteristic and noncharacteristic components. We eliminate the noncharacteristic components by a multigrid wave cycle, which employs carefully selected smoothers on each grid. We diminish the characteristic components by a learned phase function and the approximate solution of an advection-diffusion-reaction (ADR) equation, which is solved using another multigrid V-cycle on a coarser scale, referred to as the ADR cycle. The resulting solver, termed Wave-ADR-NS, enables the handling of error components with varying frequencies and overcomes constraints on the number of grid points per wavelength on coarse grids. Furthermore, we provide an efficient implementation using differentiable programming, making Wave-ADR-NS an end-to-end Helmholtz solver that incorporates parameters learned through semisupervised training. Wave-ADR-NS demonstrates robust generalization capabilities for both in-distribution and out-of-distribution velocity fields of varying difficulty. Comparative experiments with other multigrid methods validate its superior performance in solving heterogeneous 2D Helmholtz equations with wavenumbers exceeding 2000.

Förderung

  • National Key Research and Development Program of China
  • Science and Technology Innovation Program of Hunan Province
  • Science Challenge Project
  • Hunan Provincial Innovation Foundation for Postgraduate
  • National Natural Science Foundation of China

Zitieren

APA

Cui, C., Jiang, K., & Shu, S. (2025). A Neural Multigrid Solver for Helmholtz Equations with High Wavenumber and Heterogeneous Media. SIAM Journal on Scientific Computing, 47(3), C655-C679. https://doi.org/10.1137/24m1654397

Vancouver

Cui C, Jiang K, Shu S. A Neural Multigrid Solver for Helmholtz Equations with High Wavenumber and Heterogeneous Media. SIAM Journal on Scientific Computing. 2025;47(3):C655-C679. doi:10.1137/24m1654397

BibTeX
@article{Cui2025,
  author = {Cui, Chen and Jiang, Kai and Shu, Shi},
  title = {A Neural Multigrid Solver for Helmholtz Equations with High Wavenumber and Heterogeneous Media},
  journal = {SIAM Journal on Scientific Computing},
  year = {2025},
  volume = {47},
  number = {3},
  pages = {C655--C679},
  doi = {10.1137/24m1654397}
}
Kostenlos starten →