Controlling oscillations in high-order Discontinuous Galerkin schemes using artificial viscosity tuned by neural networks

•Designed an MLP network to estimate artificial viscosity in Discontinuous Galerkin schemes.•The proposed technique is free of problem-dependent parameters.•Tested with scalar conservation laws and the compressible Euler equations.•It guarantees optimal convergence rates for smooth problems and accurately detects discontinuities.•Comparison with some traditional artificial viscosity models.