Entropy stable conservative flux form neural networks

TL;DR

This paper introduces an entropy-stable conservative flux neural network that combines classical conservation laws with data-driven methods, ensuring stability, conservation, and accuracy in complex simulations including shocks and noisy data.

Contribution

It presents a novel entropy-stable flux form neural network integrating the KT scheme with slope limiting for denoising, enhancing stability and accuracy in conservation law predictions.

Findings

Achieves stability and conservation in long-term simulations.

Accurately predicts shock propagation speeds without future data.

Performs well in noisy and sparse observation environments.

Abstract

We propose an entropy-stable conservative flux form neural network (CFN) that integrates classical numerical conservation laws into a data-driven framework using the entropy-stable, second-order, and non-oscillatory Kurganov-Tadmor (KT) scheme. The proposed entropy-stable CFN uses slope limiting as a denoising mechanism, ensuring accurate predictions in both noisy and sparse observation environments, as well as in both smooth and discontinuous regions. Numerical experiments demonstrate that the entropy-stable CFN achieves both stability and conservation while maintaining accuracy over extended time domains. Furthermore, it successfully predicts shock propagation speeds in long-term simulations, {\it without} oracle knowledge of later-time profiles in the training data.