Asymptotic-Preserving Neural Networks for hyperbolic systems with diffusive scaling

TL;DR

This paper introduces Asymptotic-Preserving Neural Networks (APNNs) designed for hyperbolic systems with diffusive scaling, demonstrating improved accuracy over standard neural networks in multiscale scientific problems with limited data.

Contribution

The paper develops APNNs that maintain accuracy across multiple scales in hyperbolic systems, addressing limitations of standard DNNs and PINNs in multiscale modeling.

Findings

APNNs outperform standard DNNs and PINNs in multiscale hyperbolic systems.

APNNs are effective with limited and scattered data.

Numerical tests confirm improved accuracy of APNNs.

Abstract

With the rapid advance of Machine Learning techniques and the deep increase of availability of scientific data, data-driven approaches have started to become progressively popular across science, causing a fundamental shift in the scientific method after proving to be powerful tools with a direct impact in many areas of society. Nevertheless, when attempting to analyze dynamics of complex multiscale systems, the usage of standard Deep Neural Networks (DNNs) and even standard Physics-Informed Neural Networks (PINNs) may lead to incorrect inferences and predictions, due to the presence of small scales leading to reduced or simplified models in the system that have to be applied consistently during the learning process. In this Chapter, we will address these issues in light of recent results obtained in the development of Asymptotic-Preserving Neural Networks (APNNs) for hyperbolic models with diffusive scaling. Several numerical tests show how APNNs provide considerably better results with respect to the different scales of the problem when compared with standard DNNs and PINNs, especially when analyzing scenarios in which only little and scattered information is available.