Rational-WENO: A lightweight, physically-consistent three-point weighted essentially non-oscillatory scheme

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shahane, Shantanu, Chammas, Sheide, Bezgin, Deniz A., Buhendwa, Aaron B., Schmidt, Steffen J., Adams, Nikolaus A., Bryngelson, Spencer H., Chen, Yi-Fan, Wang, Qing, Sha, Fei, Zepeda-Núñez, Leonardo
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929500127756288
author Shahane, Shantanu
Chammas, Sheide
Bezgin, Deniz A.
Buhendwa, Aaron B.
Schmidt, Steffen J.
Adams, Nikolaus A.
Bryngelson, Spencer H.
Chen, Yi-Fan
Wang, Qing
Sha, Fei
Zepeda-Núñez, Leonardo
author_facet Shahane, Shantanu
Chammas, Sheide
Bezgin, Deniz A.
Buhendwa, Aaron B.
Schmidt, Steffen J.
Adams, Nikolaus A.
Bryngelson, Spencer H.
Chen, Yi-Fan
Wang, Qing
Sha, Fei
Zepeda-Núñez, Leonardo
contents Conventional WENO3 methods are known to be highly dissipative at lower resolutions, introducing significant errors in the pre-asymptotic regime. In this paper, we employ a rational neural network to accurately estimate the local smoothness of the solution, dynamically adapting the stencil weights based on local solution features. As rational neural networks can represent fast transitions between smooth and sharp regimes, this approach achieves a granular reconstruction with significantly reduced dissipation, improving the accuracy of the simulation. The network is trained offline on a carefully chosen dataset of analytical functions, bypassing the need for differentiable solvers. We also propose a robust model selection criterion based on estimates of the interpolation's convergence order on a set of test functions, which correlates better with the model performance in downstream tasks. We demonstrate the effectiveness of our approach on several one-, two-, and three-dimensional fluid flow problems: our scheme generalizes across grid resolutions while handling smooth and discontinuous solutions. In most cases, our rational network-based scheme achieves higher accuracy than conventional WENO3 with the same stencil size, and in a few of them, it achieves accuracy comparable to WENO5, which uses a larger stencil.
format Preprint
id arxiv_https___arxiv_org_abs_2409_09217
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rational-WENO: A lightweight, physically-consistent three-point weighted essentially non-oscillatory scheme
Shahane, Shantanu
Chammas, Sheide
Bezgin, Deniz A.
Buhendwa, Aaron B.
Schmidt, Steffen J.
Adams, Nikolaus A.
Bryngelson, Spencer H.
Chen, Yi-Fan
Wang, Qing
Sha, Fei
Zepeda-Núñez, Leonardo
Numerical Analysis
Machine Learning
Conventional WENO3 methods are known to be highly dissipative at lower resolutions, introducing significant errors in the pre-asymptotic regime. In this paper, we employ a rational neural network to accurately estimate the local smoothness of the solution, dynamically adapting the stencil weights based on local solution features. As rational neural networks can represent fast transitions between smooth and sharp regimes, this approach achieves a granular reconstruction with significantly reduced dissipation, improving the accuracy of the simulation. The network is trained offline on a carefully chosen dataset of analytical functions, bypassing the need for differentiable solvers. We also propose a robust model selection criterion based on estimates of the interpolation's convergence order on a set of test functions, which correlates better with the model performance in downstream tasks. We demonstrate the effectiveness of our approach on several one-, two-, and three-dimensional fluid flow problems: our scheme generalizes across grid resolutions while handling smooth and discontinuous solutions. In most cases, our rational network-based scheme achieves higher accuracy than conventional WENO3 with the same stencil size, and in a few of them, it achieves accuracy comparable to WENO5, which uses a larger stencil.
title Rational-WENO: A lightweight, physically-consistent three-point weighted essentially non-oscillatory scheme
topic Numerical Analysis
Machine Learning
url https://arxiv.org/abs/2409.09217