Singular layer PINN methods for Burgers' equation

TL;DR

This paper introduces sl-PINN, a novel physics-informed neural network method designed to accurately solve the viscous Burgers' equation with small viscosity, effectively capturing the interior layer behavior.

Contribution

The paper develops a new sl-PINN approach that incorporates asymptotic correctors to improve solution accuracy near interior layers in viscous Burgers' problems.

Findings

sl-PINN reduces errors near interior layers compared to traditional PINNs

The method accurately predicts solutions for low viscosity cases

Provides a better understanding of solution behavior near interior layers

Abstract

In this article, we present a new learning method called sl-PINN to tackle the one-dimensional viscous Burgers problem at a small viscosity, which results in a singular interior layer. To address this issue, we first determine the corrector that characterizes the unique behavior of the viscous flow within the interior layers by means of asymptotic analysis. We then use these correctors to construct sl-PINN predictions for both stationary and moving interior layer cases of the viscous Burgers problem. Our numerical experiments demonstrate that sl-PINNs accurately predict the solution for low viscosity, notably reducing errors near the interior layer compared to traditional PINN methods. Our proposed method offers a comprehensive understanding of the behavior of the solution near the interior layer, aiding in capturing the robust part of the training solution.