English
Related papers

Related papers: From Initial Data to Boundary Layers: Neural Netwo…

200 papers

We present a neural network-based method for learning scalar hyperbolic conservation laws. Our method replaces the traditional numerical flux in finite volume schemes with a trainable neural network while preserving the conservative…

This paper is concerned with the initial-boundary value problem for a nonlinear hyperbolic system of conservation laws. We study the boundary layers that may arise in approximations of entropy discontinuous solutions. We consider both the…

Analysis of PDEs · Mathematics 2009-11-13 K. T. Joseph , Philippe G. LeFloch

We derive new boundary conditions and implementation procedures for nonlinear initial boundary value problems that lead to energy and entropy bounded solutions. A step-by-step procedure for general nonlinear hyperbolic problems on…

Numerical Analysis · Mathematics 2024-05-10 Jan Nordström

In this paper we develop a non-diffusive neural network (NDNN) algorithm for accurately solving weak solutions to hyperbolic conservation laws. The principle is to construct these weak solutions by computing smooth local solutions in…

Numerical Analysis · Mathematics 2024-05-27 Emmanuel Lorin , Arian Novruzi

We propose and study the evolving neural network (ENN) method for solving one-dimensional scalar hyperbolic conservation laws with linear and quadratic spatial fluxes. The ENN method first represents the initial data and the inflow boundary…

Numerical Analysis · Mathematics 2023-12-13 Zhiqiang Cai , Brooke Hejnal

We propose a new entropy-compatible neural network method for scalar hyperbolic conservation laws and establish, to our knowledge, the first explicit \(L^1\) convergence rates in this setting that apply to piecewise smooth entropy…

Numerical Analysis · Mathematics 2026-05-20 Jiachuan Cao , Buyang Li , Hao Li

A novel structure-preserving numerical method to solve random hyperbolic systems of conservation laws is presented. The method uses a concept of generalized, measure-valued solutions to random conservation laws. This yields a linear partial…

Numerical Analysis · Mathematics 2025-10-29 Shaoshuai Chu , Michael Herty , Maria Lukacova-Medvidova , Yizhou Zhou

We study hyperbolic systems of one-dimensional partial differential equations under general, possibly non-local boundary conditions. A large class of evolution equations, either on individual 1-dimensional intervals or on general networks,…

Analysis of PDEs · Mathematics 2021-01-19 Marjeta Kramar Fijavž , Delio Mugnolo , Serge Nicaise

We derive rigorous bounds on the error resulting from the approximation of the solution of parametric hyperbolic scalar conservation laws with ReLU neural networks. We show that the approximation error can be made as small as desired with…

Numerical Analysis · Mathematics 2022-07-18 Tim De Ryck , Siddhartha Mishra

We discuss the existence and uniqueness of discontinuous solutions to adjoint problems associated with nonlinear hyperbolic systems of conservation laws. By generalizing the Haar method for Glimm-type approximations to hyperbolic systems,…

Analysis of PDEs · Mathematics 2008-12-23 Philippe G. LeFloch

We derive entropy conserving and entropy dissipative overlapping domain formulations for systems of nonlinear hyperbolic equations in conservation form, such as would be approximated by overset mesh methods. The entropy conserving…

Numerical Analysis · Mathematics 2022-10-05 David A. Kopriva , Gregor J. Gassner , Jan Nordstrom

We present a new approach to analyze the validation of weakly nonlinear geometric optics for entropy solutions of nonlinear hyperbolic systems of conservation laws whose eigenvalues are allowed to have constant multiplicity and…

Analysis of PDEs · Mathematics 2012-12-27 Gui-Qiang Chen , Wei Xiang , Yongqian Zhang

We consider the approximation of entropy solutions of nonlinear hyperbolic conservation laws using neural networks. We provide explicit computations that highlight why classical PINNs will not work for discontinuous solutions to nonlinear…

Numerical Analysis · Mathematics 2023-12-20 Aidan Chaumet , Jan Giesselmann

We study a Neumann type initial-boundary value problem for strongly degenerate parabolic-hyperbolic equations under the nonlinearity-diffusivity condition. We suggest a notion of entropy solution for this problem and prove its uniqueness.…

Analysis of PDEs · Mathematics 2014-07-09 Yuxi Hu , Yachun Li

The solution to partial differential equations using deep learning approaches has shown promising results for several classes of initial and boundary-value problems. However, their ability to surpass, particularly in terms of accuracy,…

Numerical Analysis · Mathematics 2023-08-23 Ziad Aldirany , Régis Cottereau , Marc Laforest , Serge Prudhomme

Neural networks have dramatically increased our capacity to learn from large, high-dimensional datasets across innumerable disciplines. However, their decisions are not easily interpretable, their computational costs are high, and building…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Mackenzie J. Meni , Ryan T. White , Michael Mayo , Kevin Pilkiewicz

This paper presents a data-driven finite volume method for solving 1D and 2D hyperbolic partial differential equations. This work builds upon the prior research incorporating a data-driven finite-difference approximation of smooth solutions…

Numerical Analysis · Mathematics 2025-02-25 Guillaume de Romémont , Florent Renac , Jorge Nunez , Francisco Chinesta

We propose a neural entropy-stable conservative flux form neural network (NESCFN) for learning hyperbolic conservation laws and their associated entropy functions directly from solution trajectories, without requiring any predefined…

Numerical Analysis · Mathematics 2025-07-03 Lizuo Liu , Lu Zhang , Anne Gelb

In this article, we present a numerical approach to ensure the preservation of physical bounds on the solutions to linear and nonlinear hyperbolic convection-reaction problems at the discrete level. We provide a rigorous framework for error…

Numerical Analysis · Mathematics 2025-01-22 Ben S. Ashby , Abdalaziz Hamdan , Tristan Pryer

Physics-informed neural network architectures have emerged as a powerful tool for developing flexible PDE solvers which easily assimilate data, but face challenges related to the PDE discretization underpinning them. By instead adapting a…

Numerical Analysis · Mathematics 2020-12-11 Ravi G. Patel , Indu Manickam , Nathaniel A. Trask , Mitchell A. Wood , Myoungkyu Lee , Ignacio Tomas , Eric C. Cyr
‹ Prev 1 2 3 10 Next ›