Efficient Numerical Wave Propagation Enhanced By An End-to-End Deep Learning Model

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kaiser, Luis, Tsai, Richard, Klingenberg, Christian
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909789332701184
author Kaiser, Luis
Tsai, Richard
Klingenberg, Christian
author_facet Kaiser, Luis
Tsai, Richard
Klingenberg, Christian
contents In a variety of scientific and engineering domains, the need for high-fidelity and efficient solutions for high-frequency wave propagation holds great significance. Recent advances in wave modeling use sufficiently accurate fine solver outputs to train a neural network that enhances the accuracy of a fast but inaccurate coarse solver. In this paper we build upon the work of Nguyen and Tsai (2023) and present a novel unified system that integrates a numerical solver with a deep learning component into an end-to-end framework. In the proposed setting, we investigate refinements to the network architecture and data generation algorithm. A stable and fast solver further allows the use of Parareal, a parallel-in-time algorithm to correct high-frequency wave components. Our results show that the cohesive structure improves performance without sacrificing speed, and demonstrate the importance of temporal dynamics, as well as Parareal, for accurate wave propagation.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02304
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Numerical Wave Propagation Enhanced By An End-to-End Deep Learning Model
Kaiser, Luis
Tsai, Richard
Klingenberg, Christian
Analysis of PDEs
Machine Learning
In a variety of scientific and engineering domains, the need for high-fidelity and efficient solutions for high-frequency wave propagation holds great significance. Recent advances in wave modeling use sufficiently accurate fine solver outputs to train a neural network that enhances the accuracy of a fast but inaccurate coarse solver. In this paper we build upon the work of Nguyen and Tsai (2023) and present a novel unified system that integrates a numerical solver with a deep learning component into an end-to-end framework. In the proposed setting, we investigate refinements to the network architecture and data generation algorithm. A stable and fast solver further allows the use of Parareal, a parallel-in-time algorithm to correct high-frequency wave components. Our results show that the cohesive structure improves performance without sacrificing speed, and demonstrate the importance of temporal dynamics, as well as Parareal, for accurate wave propagation.
title Efficient Numerical Wave Propagation Enhanced By An End-to-End Deep Learning Model
topic Analysis of PDEs
Machine Learning
url https://arxiv.org/abs/2402.02304