Detecting troubled-cells on two-dimensional unstructured grids using a neural network

DOI10.1016/J.JCP.2019.07.043zbMath1453.65301OpenAlexW2898842442WikidataQ127438993 ScholiaQ127438993MaRDI QIDQ2222514

Deep Ray, Jan S. Hesthaven

Publication date: 27 January 2021

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: http://infoscience.epfl.ch/record/258044

zbMATH Keywords

conservation lawsunstructured meshartificial neural networkdiscontinuous Galerkintroubled-cell indicator

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Hyperbolic conservation laws (35L65) Finite element methods applied to problems in fluid mechanics (76M10) Finite element, Rayleigh-Ritz and Galerkin methods for initial value and initial-boundary value problems involving PDEs (65M60) Mesh generation, refinement, and adaptive methods for the numerical solution of initial value and initial-boundary value problems involving PDEs (65M50)

Related Items (22)

Using deep learning to extend the range of air pollution monitoring and forecasting ⋮ A neural network based shock detection and localization approach for discontinuous Galerkin methods ⋮ Meta-mgnet: meta multigrid networks for solving parameterized partial differential equations ⋮ Mean-field and kinetic descriptions of neural differential equations ⋮ A simplified multilayer perceptron detector for the hybrid WENO scheme ⋮ A data-driven shock capturing approach for discontinuous Galerkin methods ⋮ A characteristic-featured shock wave indicator for conservation laws based on training an artificial neuron ⋮ Troubled-cell indication using K-means clustering with unified parameters ⋮ Learning-based local weighted least squares for algebraic multigrid method ⋮ Using deep neural networks for detecting spurious oscillations in discontinuous Galerkin solutions of convection-dominated convection-diffusion equations ⋮ Continuous limits of residual neural networks in case of large input data ⋮ A Reinforcement Learning Based Slope Limiter for Two-Dimensional Finite Volume Schemes ⋮ An indicator-based hybrid limiter in discontinuous Galerkin methods for hyperbolic conservation laws ⋮ Artificial neural network-augmented stabilized finite element method ⋮ A moment limiter for the discontinuous Galerkin method on unstructured tetrahedral meshes ⋮ A new WENO weak Galerkin finite element method for time dependent hyperbolic equations ⋮ A hybrid first-order and WENO scheme for the high-resolution and computationally efficient modeling of pollutant transport ⋮ Convolution Neural Network Shock Detector for Numerical Solution of Conservation Laws ⋮ A priori neural networks versus a posteriori MOOD loop: a high accurate 1D FV scheme testing bed ⋮ A New Troubled-Cell Indicator for Discontinuous Galerkin Methods Using K-Means Clustering ⋮ Enhanced fifth order WENO shock-capturing schemes with deep learning ⋮ Three Indication Variables and Their Performance for the Troubled-Cell Indicator using K-Means Clustering

Uses Software

• Spearmint
• Hyperopt
• Adam
• PDE-Net

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• \textit{A posteriori} subcell limiting of the discontinuous Galerkin finite element method for hyperbolic conservation laws
• A new troubled-cell indicator for discontinuous Galerkin methods for hyperbolic conservation laws
• Hermite WENO schemes and their application as limiters for Runge-Kutta discontinuous Galerkin method. II: Two dimensional case
• An explicit construction of interpolation nodes on the simplex
• ENO schemes with subcell resolution
• The numerical simulation of two-dimensional fluid flow with strong shocks
• TVB Runge-Kutta local projection discontinuous Galerkin finite element method for conservation laws. III: One-dimensional systems
• The Runge-Kutta discontinuous Galerkin method for conservation laws. I: Multidimensional systems
• Parallel, adaptive finite element methods for conservation laws
• Hermite WENO schemes and their application as limiters for Runge-Kutta discontinuous Galerkin method: One-dimensional case.
• Shock detection and limiting with discontinuous Galerkin methods for hyperbolic conservation laws.
• Runge--Kutta discontinuous Galerkin methods for convection-dominated problems
• Hidden physics models: machine learning of nonlinear partial differential equations
• An artificial neural network as a troubled-cell indicator
• A sub-cell based indicator for troubled zones in RKDG schemes and a novel class of hybrid RKDG+HWENO schemes
• Limiters for high-order discontinuous Galerkin methods
• Strong Stability-Preserving High-Order Time Discretization Methods
• Arbitrarily High-order Accurate Entropy Stable Essentially Nonoscillatory Schemes for Systems of Conservation Laws
• Automated Parameters for Troubled-Cell Indicators Using Outlier Detection
• TVB Runge-Kutta Local Projection Discontinuous Galerkin Finite Element Method for Conservation Laws II: General Framework
• Numerical Methods for Conservation Laws
• Runge--Kutta Discontinuous Galerkin Method Using WENO Limiters
• Solution of two-dimensional Riemann problems for gas dynamics without Riemann problem solvers
• A Comparison of Troubled-Cell Indicators for Runge--Kutta Discontinuous Galerkin Methods Using Weighted Essentially Nonoscillatory Limiters
• Hyperbolic Conservation Laws in Continuum Physics
• A problem-independent limiter for high-order Runge-Kutta discontinuous Galerkin methods

This page was built for publication: Detecting troubled-cells on two-dimensional unstructured grids using a neural network