An artificial neural network as a troubled-cell indicator

DOI10.1016/j.jcp.2018.04.029zbMath1415.65229OpenAlexW2768535327MaRDI QIDQ2424512

Deep Ray, Jan S. Hesthaven

Publication date: 25 June 2019

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

Full work available at URL: http://infoscience.epfl.ch/record/232425

zbMATH Keywords

conservation lawdiscontinuous Galerkin methodartificial neural networktroubled-cell indicatorlimiting

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Hyperbolic conservation laws (35L65) Finite element, Rayleigh-Ritz and Galerkin methods for initial value and initial-boundary value problems involving PDEs (65M60)

Related Items

A \(p\)-weighted limiter for the discontinuous Galerkin method on one-dimensional and two-dimensional triangular grids, Machine learning design of volume of fluid schemes for compressible flows, Using deep learning to extend the range of air pollution monitoring and forecasting, Data-driven deep learning of partial differential equations in modal space, A neural network based shock detection and localization approach for discontinuous Galerkin methods, On generalized residual network for deep learning of unknown dynamical systems, A data-driven high order sub-cell artificial viscosity for the discontinuous Galerkin spectral element method, Hyperbolic balance laws: modeling, analysis, and numerics. Abstracts from the workshop held February 28 -- March 6, 2021 (hybrid meeting), A characteristic-featured shock wave indicator on unstructured grids based on training an artificial neuron, Refinement of polygonal grids using convolutional neural networks with applications to polygonal discontinuous Galerkin and virtual element methods, Mean-field and kinetic descriptions of neural differential equations, Convergence Rate Analysis for Deep Ritz Method, A simplified multilayer perceptron detector for the hybrid WENO scheme, A data-driven shock capturing approach for discontinuous Galerkin methods, Deep learning of biological models from data: applications to ODE models, A characteristic-featured shock wave indicator for conservation laws based on training an artificial neuron, Multiscale parareal algorithm for long-time mesoscopic simulations of microvascular blood flow in zebrafish, A hybrid inference system for improved curvature estimation in the level-set method using machine learning, Surrogate convolutional neural network models for steady computational fluid dynamics simulations, Deep Neural Network Surrogates for Nonsmooth Quantities of Interest in Shape Uncertainty Quantification, Troubled-cell indication using K-means clustering with unified parameters, Error-correcting neural networks for two-dimensional curvature computation in the level-set method, Machine learning based refinement strategies for polyhedral grids with applications to virtual element and polyhedral discontinuous Galerkin methods, An edge detector based on artificial neural network with application to hybrid compact-WENO finite difference scheme, A perspective on machine learning methods in turbulence modeling, Neural control of discrete weak formulations: Galerkin, least squares \& minimal-residual methods with quasi-optimal weights, Using deep neural networks for detecting spurious oscillations in discontinuous Galerkin solutions of convection-dominated convection-diffusion equations, Neural network-based limiter with transfer learning, Continuous limits of residual neural networks in case of large input data, Agglomeration of polygonal grids using graph neural networks with applications to multigrid solvers, Machine learning algorithms for three-dimensional mean-curvature computation in the level-set method, A learned conservative semi-Lagrangian finite volume scheme for transport simulations, FC-based shock-dynamics solver with neural-network localized artificial-viscosity assignment, An indicator-based hybrid limiter in discontinuous Galerkin methods for hyperbolic conservation laws, Artificial neural network-augmented stabilized finite element method, Small collaboration: Advanced numerical methods for nonlinear hyperbolic balance laws and their applications. Abstracts from the small collaboration held August 29 -- September 4, 2021 (hybrid meeting), An Adaptive Multiresolution Discontinuous Galerkin Method with Artificial Viscosity for Scalar Hyperbolic Conservation Laws in Multidimensions, Data driven governing equations approximation using deep neural networks, Detecting troubled-cells on two-dimensional unstructured grids using a neural network, A new WENO weak Galerkin finite element method for time dependent hyperbolic equations, A Generalization of a Troubled-Cell Indicator to $h$-Adaptive Meshes for Discontinuous Galerkin Methods, A hybrid first-order and WENO scheme for the high-resolution and computationally efficient modeling of pollutant transport, Troubled-Cell Indicator based on Mean Value Property for Hybrid WENO schemes, Convolution Neural Network Shock Detector for Numerical Solution of Conservation Laws, Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning, A priori neural networks versus a posteriori MOOD loop: a high accurate 1D FV scheme testing bed, Iterative surrogate model optimization (ISMO): an active learning algorithm for PDE constrained optimization with deep neural networks, A machine-learning minimal-residual (ML-MRes) framework for goal-oriented finite element discretizations, A New Troubled-Cell Indicator for Discontinuous Galerkin Methods Using K-Means Clustering, A machine learning framework for data driven acceleration of computations of differential equations, Multi-fidelity regression using artificial neural networks: efficient approximation of parameter-dependent output quantities, Optimal staggered-grid finite-difference method for wave modeling based on artificial neural networks, Deep learning observables in computational fluid dynamics, Controlling oscillations in high-order discontinuous Galerkin schemes using artificial viscosity tuned by neural networks, Constraint-aware neural networks for Riemann problems, A Hermite WENO scheme with artificial linear weights for hyperbolic conservation laws, Enhancing Accuracy of Deep Learning Algorithms by Training with Low-Discrepancy Sequences, Error-correcting neural networks for semi-Lagrangian advection in the level-set method, Adaptive numerical dissipation control for high-order \(k\)-exact reconstruction schemes on vertex-centered unstructured grids using artificial neural networks, A multi-level procedure for enhancing accuracy of machine learning algorithms, Three Indication Variables and Their Performance for the Troubled-Cell Indicator using K-Means Clustering

Uses Software

• TensorFlow
• ImageNet
• Adam
• AlexNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On positivity-preserving high order discontinuous Galerkin schemes for compressible Euler equations on rectangular meshes
• Uniformly high order accurate essentially non-oscillatory schemes. III. (Reprint)
• A new troubled-cell indicator for discontinuous Galerkin methods for hyperbolic conservation laws
• On maximum-principle-satisfying high order schemes for scalar conservation laws
• The numerical simulation of two-dimensional fluid flow with strong shocks
• Efficient implementation of essentially nonoscillatory shock-capturing schemes. II
• TVB Runge-Kutta local projection discontinuous Galerkin finite element method for conservation laws. III: One-dimensional systems
• A survey of several finite difference methods for systems of nonlinear hyperbolic conservation laws
• The Runge-Kutta discontinuous Galerkin method for conservation laws. I: Multidimensional systems
• Weighted essentially non-oscillatory schemes
• Automatic differentiation of algorithms
• Runge--Kutta discontinuous Galerkin methods for convection-dominated problems
• Enhanced robustness of the hybrid compact-WENO finite difference scheme for hyperbolic conservation laws with multi-resolution analysis and Tukey's boxplot method
• On the construction, comparison, and local characteristic decomposition for high-order central WENO schemes
• Towards the ultimate conservative difference scheme. V. A second-order sequel to Godunov's method
• Strong Stability-Preserving High-Order Time Discretization Methods
• 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
• Entropy stability theory for difference approximations of nonlinear conservation laws and related time-dependent problems
• Finite Volume Methods for Hyperbolic Problems
• Runge--Kutta Discontinuous Galerkin Method Using WENO Limiters
• A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate Function
• A Comparison of Troubled-Cell Indicators for Runge--Kutta Discontinuous Galerkin Methods Using Weighted Essentially Nonoscillatory Limiters
• On Information and Sufficiency
• Weak solutions of nonlinear hyperbolic equations and their numerical computation
• A logical calculus of the ideas immanent in nervous activity
• Hyperbolic Conservation Laws in Continuum Physics
• Approximation by superpositions of a sigmoidal function