Physics-Informed Neural Network Method for Parabolic Differential Equations with Sharply Perturbed Initial Conditions

TL;DR

This paper introduces a normalized PINN approach for parabolic PDEs with sharply perturbed initial conditions, improving accuracy and efficiency through adaptive sampling and optimized loss weights.

Contribution

The paper proposes a normalization technique and adaptive sampling scheme that enhance PINN accuracy for parabolic equations with perturbed initial conditions.

Findings

Normalization reduces approximation error significantly.

Adaptive sampling improves solution accuracy with fewer residual points.

Optimized loss weights lead to more accurate PINN solutions.

Abstract

In this paper, we develop a physics-informed neural network (PINN) model for parabolic problems with a sharply perturbed initial condition. As an example of a parabolic problem, we consider the advection-dispersion equation (ADE) with a point (Gaussian) source initial condition. In the $d$-dimensional ADE, perturbations in the initial condition decay with time $t$ as $t^{-d/2}$, which can cause a large approximation error in the PINN solution. Localized large gradients in the ADE solution make the (common in PINN) Latin hypercube sampling of the equation's residual highly inefficient. Finally, the PINN solution of parabolic equations is sensitive to the choice of weights in the loss function. We propose a normalized form of ADE where the initial perturbation of the solution does not decrease in amplitude and demonstrate that this normalization significantly reduces the PINN approximation error. We propose criteria for weights in the loss function that produce a more accurate PINN solution than those obtained with the weights selected via other methods. Finally, we proposed an adaptive sampling scheme that significantly reduces the PINN solution error for the same number of the sampling (residual) points. We demonstrate the accuracy of the proposed PINN model for forward, inverse, and backward ADEs.