A neural network based shock detection and localization approach for discontinuous Galerkin methods

AD Beck, J Zeifang, A Schwarz, DG Flad - Journal of Computational …, 2020 - Elsevier
The stable and accurate approximation of discontinuities such as shocks on a finite
computational mesh is a challenging task. Detection of shocks or strong discontinuities in …

An unsupervised machine-learning-based shock sensor: Application to high-order supersonic flow solvers

A Mateo-Gabín, K Tlales, E Valero, E Ferrer… - Expert Systems with …, 2025 - Elsevier
We present a novel unsupervised machine-learning shock sensor based on Gaussian
Mixture Models (GMMs). The proposed GMM sensor demonstrates remarkable accuracy in …

Using Deep Neural Networks for Detecting Spurious Oscillations in Discontinuous Galerkin Solutions of Convection-Dominated Convection–Diffusion Equations

D Frerichs-Mihov, L Henning, V John - Journal of Scientific Computing, 2023 - Springer
Standard discontinuous Galerkin finite element solutions to convection-dominated
convection–diffusion equations usually possess sharp layers but also exhibit large spurious …

Neural network-based limiter with transfer learning

R Abgrall, M Han Veiga - Communications on Applied Mathematics and …, 2023 - Springer
Recent works have shown that neural networks are promising parameter-free limiters for a
variety of numerical schemes (Morgan et al. in A machine learning approach for detecting …

A priori neural networks versus a posteriori mood loop: a high accurate 1d fv scheme testing bed

A Bourriaud, R Loubère, R Turpault - Journal of Scientific Computing, 2020 - Springer
In this work we present an attempt to replace an a posteriori MOOD loop used in a high
accurate Finite Volume (FV) scheme by a trained artificial Neural Network (NN). The MOOD …

Machine learning approaches for the solution of the riemann problem in fluid dynamics: a case study

V Gyrya, M Shashkov, A Skurikhin… - … on Applied Mathematics …, 2024 - Springer
We present our results by using a machine learning (ML) approach for the solution of the
Riemann problem for the Euler equations of fluid dynamics. The Riemann problem is an …

Artificial neural network-augmented stabilized finite element method

S Yadav, S Ganesan - Journal of Computational Physics, 2024 - Elsevier
An artificial neural network-augmented Streamline Upwind/Petrov-Galerkin finite element
scheme (SPDE-NetII) is proposed for solving singularly perturbed partial differential …

AI-augmented stabilized finite element method

S Yadav, S Ganesan - arxiv preprint arxiv:2211.13418, 2022 - arxiv.org
An artificial intelligence-augmented Streamline Upwind/Petrov-Galerkin finite element
scheme (AiStab-FEM) is proposed for solving singularly perturbed partial differential …

On the choice of hyper-parameters of artificial neural networks for stabilized finite element schemes

SM Joshi, T Anandh, B Teja, S Ganesan - International Journal of …, 2021 - Springer
This paper provides guidelines for an effective artificial neural networks (ANNs) design to
aid stabilized finite element schemes. In particular, ANNs are used to estimate the …

On slope limiting and deep learning techniques for the numerical solution to convection-dominated convection-diffusion problems

D Frerichs-Mihov - 2023 - refubium.fu-berlin.de
As the first main topic, several slope-limiting techniques from the literature are presented,
and various novel methods are proposed. These post-processing techniques aim to …