Physics-Informed Neural Network Method for Parabolic Differential Equations with Sharply Perturbed Initial Conditions
This work addresses inefficiencies in PINNs for specific parabolic problems, offering incremental improvements in accuracy and sampling for researchers in computational physics and machine learning.
The paper tackles the challenge of using physics-informed neural networks (PINNs) to solve parabolic differential equations with sharply perturbed initial conditions, such as the advection-dispersion equation, by introducing a normalized form of the equation, criteria for loss function weights, and an adaptive sampling scheme, which significantly reduce approximation errors and improve accuracy for forward, inverse, and backward problems.
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.