• Corpus ID: 239050012

Finite Volume Least-Squares Neural Network (FV-LSNN) Method for Scalar Nonlinear Hyperbolic Conservation Laws

@article{Cai2021FiniteVL,
  title={Finite Volume Least-Squares Neural Network (FV-LSNN) Method for Scalar Nonlinear Hyperbolic Conservation Laws},
  author={Zhiqiang Cai and Jingshuang Chen and Min Liu},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.10895}
}
  • Zhiqiang Cai, Jingshuang Chen, Min Liu
  • Published 21 October 2021
  • Computer Science, Mathematics
  • ArXiv
In [4], we introduced the least-squares ReLU neural network (LSNN) method for solving the linear advection-reaction problem with discontinuous solution and showed that the number of degrees of freedom for the LSNN method is significantly less than that of traditional mesh-based methods. The LSNN method is a discretization of an equivalent least-squares (LS) formulation in the class of neural network functions with the ReLU activation function; and evaluation of the LS functional is done by… 
Least-Squares ReLU Neural Network (LSNN) Method For Scalar Nonlinear Hyperbolic Conservation Law
TLDR
Numerical results of some test problems show that the LSNN method is capable of approximating the discontinuous interface of the underlying problem automatically through the free breaking lines of the ReLU neural network.

References

SHOWING 1-10 OF 31 REFERENCES
Least-Squares ReLU Neural Network (LSNN) Method For Scalar Nonlinear Hyperbolic Conservation Law
TLDR
Numerical results of some test problems show that the LSNN method is capable of approximating the discontinuous interface of the underlying problem automatically through the free breaking lines of the ReLU neural network.
Least-Squares ReLU Neural Network (LSNN) Method For Linear Advection-Reaction Equation
TLDR
Numerical results of some benchmark test problems show that the least-squares ReLU neural network method can not only approximate the solution with the least number of parameters, but also avoid the common Gibbs phenomena along the discontinuous interface.
Least-Squares Finite Element Methods and Algebraic Multigrid Solvers for Linear Hyperbolic PDEs
TLDR
Finite element convergence is proved for conforming and nonconforming (discontinuous) LSFEMs that are similar to previously proposed methods but for which no rigorous convergence proofs have been given in the literature.
Numerical Conservation Properties of H(div)-Conforming Least-Squares Finite Element Methods for the Burgers Equation
TLDR
Weak conservation theorems that are analogous to the Lax--Wendroff theorem for conservative finite difference methods are proved for the H(div)-conforming LSFEMs, illustrating that discrete exact conservation is not a necessary condition for numerical conservation but can be replaced by minimization in a suitable continuous norm.
Adaptive Two-Layer ReLU Neural Network: II. Ritz Approximation to Elliptic PDEs
TLDR
It is proved that the Ritz approximation is the best approximation in the energy norm; moreover, effect of numerical integration for the Ritzer approximation is analyzed as well.
DISCONTINUOUS GALERKIN METHODS FOR FIRST-ORDER HYPERBOLIC PROBLEMS
The main aim of this paper is to highlight that, when dealing with DG methods for linear hyperbolic equations or advection-dominated equations, it is much more convenient to write the upwind
A class of discontinuous Petrov-Galerkin methods. Part III
We continue our theoretical and numerical study on the Discontinuous Petrov-Galerkin method with optimal test functions in context of 1D and 2D convection-dominated diffusion problems and
Improved Least-squares Error Estimates for Scalar Hyperbolic Problems
Abstract We consider an L_2-norm least-squares principle for a scalar hyperbolic problem. A proper variational framework for the associated finite element method is developed and studied. Analysis of
Adaptive Petrov-Galerkin Methods for First Order Transport Equations
TLDR
Stable variational formulations are proposed for certain linear, unsymmetric operators with first order transport equations in bounded domains serving as the primary focus of this paper to adaptively resolve anisotropic solution features such as propagating singularities.
Nodal Discontinuous Galerkin Methods: Algorithms, Analysis, and Applications
The text offers an introduction to the key ideas, basic analysis, and efficient implementation of discontinuous Galerkin finite element methods (DG-FEM) for the solution of partial differential
...
1
2
3
4
...