Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation
SIAM Journal on Scientific Computing · 2023-06 · 45 (3) · S127-S151
DOI: 10.1137/21m1433514 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 01.08.2022. Verfasst von Yael Azulay und 1 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: Israeli Council for Higher Education, Israel Science Foundation.
Abstract (Originalsprache)
In this paper, we present a data-driven approach to iteratively solve the discrete heterogeneous Helmholtz equation at high wavenumbers. In our approach, we combine classical iterative solvers with convolutional neural networks (CNNs) to form a preconditioner which is applied within a Krylov solver. For the preconditioner, we use a CNN of type U-Net that operates in conjunction with multigrid ingredients. Two types of preconditioners are proposed: (1) U-Net as a coarse grid solver and (2) U-Net as a deflation operator with shifted Laplacian V-cycles. Following our training scheme and data-augmentation, our CNN preconditioner can generalize over residuals and a relatively general set of wave slowness models. On top of that, we also offer an encoder-solver framework where an “encoder" network generalizes over the medium and sends context vectors to another “solver" network, which generalizes over the right-hand sides. We show that this option is more robust and efficient than the standalone variant. Last, we also offer a mini-retraining procedure, to improve the solver after the model is known. This option is beneficial when solving multiple right-hand sides, like in inverse problems. We demonstrate the efficiency and generalization abilities of our approach on a variety of two-dimensional problems.
Förderung
- Israeli Council for Higher Education
- Israel Science Foundation
Zitieren
APA
Azulay, Y., & Treister, E. (2023). Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation. SIAM Journal on Scientific Computing, 45(3), S127-S151. https://doi.org/10.1137/21m1433514
Vancouver
Azulay Y, Treister E. Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation. SIAM Journal on Scientific Computing. 2023;45(3):S127-S151. doi:10.1137/21m1433514
BibTeX
@article{Azulay2023,
author = {Azulay, Yael and Treister, Eran},
title = {Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation},
journal = {SIAM Journal on Scientific Computing},
year = {2023},
volume = {45},
number = {3},
pages = {S127--S151},
doi = {10.1137/21m1433514}
}
EUVIMED