Neural network-based limiter with transfer learning

DOI10.1007/s42967-020-00087-1zbMath1524.65699arXiv1912.09274OpenAlexW3088135077MaRDI QIDQ6098315

Maria Han Veiga, Remi Abgrall

Publication date: 13 June 2023

Published in: Communications on Applied Mathematics and Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.09274

zbMATH Keywords

limitersneural networkstransfer learningdomain adaptation

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Finite element, Rayleigh-Ritz and Galerkin methods for initial value and initial-boundary value problems involving PDEs (65M60) Multistep, Runge-Kutta and extrapolation methods for ordinary differential equations (65L06) Complexity and performance of numerical algorithms (65Y20) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65M99) Packaged methods for numerical algorithms (65Y15) PDEs on graphs and networks (ramified or polygonal spaces) (35R02)

Related Items

Applications of limiters, neural networks and polynomial annihilation in higher-order FD/FV schemes ⋮ Using deep neural networks for detecting spurious oscillations in discontinuous Galerkin solutions of convection-dominated convection-diffusion equations ⋮ Preface to the focused issue on high-order numerical methods for evolutionary PDEs ⋮ Convolution Neural Network Shock Detector for Numerical Solution of Conservation Laws

Cites Work

• Unnamed Item
• On high order strong stability preserving Runge-Kutta and multi step time discretizations
• Application of conservative residual distribution schemes to the solution of the shallow water equations on unstructured meshes
• Explicit Runge-Kutta residual distribution schemes for time dependent problems: second order case
• Residual distribution schemes: current status and future trends
• The Runge-Kutta discontinuous Galerkin method for conservation laws. I: Multidimensional systems
• Parallel, adaptive finite element methods for conservation laws
• Practical mathematical optimization. An introduction to basic optimization theory and classical and new gradient-based algorithms.
• High-order residual distribution scheme for the time-dependent Euler equations of fluid dynamics
• A neural network based shock detection and localization approach for discontinuous Galerkin methods
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• \textit{A posteriori} correction of high-order discontinuous Galerkin scheme through subcell finite volume formulation and flux reconstruction
• An artificial neural network as a troubled-cell indicator
• Limiters for high-order discontinuous Galerkin methods
• Continuous interior penalty finite element method for the time-dependent Navier-Stokes equations: space discretization and convergence
• ``\textit{A posteriori} limited high order and robust schemes for transient simulations of fluid flows in gas dynamics
• Multi-dimensional Optimal Order Detection (MOOD) — a Very High-Order Finite Volume Scheme for Conservation Laws on Unstructured Meshes
• On a Class of High Resolution Total-Variation-Stable Finite-Difference Schemes
• Deep, Narrow Sigmoid Belief Networks Are Universal Approximators
• TVB Runge-Kutta Local Projection Discontinuous Galerkin Finite Element Method for Conservation Laws II: General Framework
• Optimization Methods for Large-Scale Machine Learning
• Solution of two-dimensional Riemann problems for gas dynamics without Riemann problem solvers
• Weak solutions of nonlinear hyperbolic equations and their numerical computation