Enhanced fifth order WENO Shock-Capturing Schemes with Deep Learning

by   Tatiana Kossaczká, et al.

In this paper we enhance the well-known fifth order WENO shock-capturing scheme by using deep learning techniques. This fine-tuning of an existing algorithm is implemented by training a rather small neural network to modify the smoothness indicators of the WENO scheme in order to improve the numerical results especially at discontinuities. In our approach no further post-processing is needed to ensure the consistency of the method, which simplifies the method and increases the effect of the neural network. Moreover, the convergence of the resulting scheme can be theoretically proven. We demonstrate our findings with the inviscid Burgers' equation, the Buckley-Leverett equation and the 1-D Euler equations of gas dynamics. Hereby we investigate the classical Sod problem and the Lax problem and show that our novel method outperforms the classical fifth order WENO schemes in simulations where the numerical solution is too diffusive or tends to overshoot at shocks.


page 1

page 2

page 3

page 4


Enhancement of shock-capturing methods via machine learning

In recent years, machine learning has been used to create data-driven so...

On the numerical overshoots of shock-capturing schemes

This note introduces a simple metric for benchmarking shock-capturing sc...

Data-driven discovery of Bäcklund transforms and soliton evolution equations via deep neural network learning schemes

We introduce a deep neural network learning scheme to learn the Bäcklund...

A deep learning based nonlinear upscaling method for transport equations

We will develop a nonlinear upscaling method for nonlinear transport equ...

How to Design A Generic Accuracy-Enhancing Filter for Discontinuous Galerkin Methods

Higher-order accuracy (order of k+1 in the L^2 norm) is one of the well ...

Arc length based WENO scheme for Hamilton-Jacobi Equations

In this article, novel smoothness indicators are presented for calculati...

A multiscale scheme accurately simulates macroscale shocks in an equation-free framework

Scientists and engineers often create accurate, trustworthy, computation...