Saved in:
Bibliographic Details
Main Authors: Sun, Qi, Liu, Zhenjiang, Ju, Lili, Xu, Xuejun
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.05382
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909538149466112
author Sun, Qi
Liu, Zhenjiang
Ju, Lili
Xu, Xuejun
author_facet Sun, Qi
Liu, Zhenjiang
Ju, Lili
Xu, Xuejun
contents Deep learning methods, which exploit auto-differentiation to compute derivatives without dispersion or dissipation errors, have recently emerged as a compelling alternative to classical mesh-based numerical schemes for solving hyperbolic conservation laws. However, solutions to hyperbolic problems are often piecewise smooth, posing challenges for training of neural networks to capture solution discontinuities and jumps across interfaces. In this paper, we propose a novel lift-and-embed learning method to effectively resolve these challenges. The proposed method comprises three innovative components: (i) embedding the Rankine-Hugoniot condition within a one-order higher-dimensional space by including an augmented variable; (ii) utilizing neural networks to handle the increased dimensionality and address both linear and nonlinear problems within a unified mesh-free learning framework; and (iii) projecting the trained model back onto the original physical domain to obtain the approximate solution. Notably, the location of discontinuities also can be treated as trainable parameters in our method and inferred concurrently with the training of neural network solutions. With collocation points sampled only on piecewise surfaces rather than fulfilling the whole lifted space, we demonstrate through extensive numerical experiments that our method can efficiently and accurately solve scalar hyperbolic equations with discontinuous solutions without spurious smearing or oscillations.
format Preprint
id arxiv_https___arxiv_org_abs_2411_05382
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Lift-and-Embed Learning Methods for Solving Scalar Hyperbolic Equations with Discontinuous Solutions
Sun, Qi
Liu, Zhenjiang
Ju, Lili
Xu, Xuejun
Numerical Analysis
35L60, 35L67
Deep learning methods, which exploit auto-differentiation to compute derivatives without dispersion or dissipation errors, have recently emerged as a compelling alternative to classical mesh-based numerical schemes for solving hyperbolic conservation laws. However, solutions to hyperbolic problems are often piecewise smooth, posing challenges for training of neural networks to capture solution discontinuities and jumps across interfaces. In this paper, we propose a novel lift-and-embed learning method to effectively resolve these challenges. The proposed method comprises three innovative components: (i) embedding the Rankine-Hugoniot condition within a one-order higher-dimensional space by including an augmented variable; (ii) utilizing neural networks to handle the increased dimensionality and address both linear and nonlinear problems within a unified mesh-free learning framework; and (iii) projecting the trained model back onto the original physical domain to obtain the approximate solution. Notably, the location of discontinuities also can be treated as trainable parameters in our method and inferred concurrently with the training of neural network solutions. With collocation points sampled only on piecewise surfaces rather than fulfilling the whole lifted space, we demonstrate through extensive numerical experiments that our method can efficiently and accurately solve scalar hyperbolic equations with discontinuous solutions without spurious smearing or oscillations.
title Lift-and-Embed Learning Methods for Solving Scalar Hyperbolic Equations with Discontinuous Solutions
topic Numerical Analysis
35L60, 35L67
url https://arxiv.org/abs/2411.05382