Asymptotic-Preserving Neural Networks for Multiscale Time-Dependent Linear Transport Equations

Abstract

In this paper we develop a neural network for the numerical simulation of time-dependent linear transport equations with diffusive scaling and uncertainties. The goal of the network is to resolve the computational challenges of curse-of-dimensionality and multiple scales of the problem. We first show that a standard Physics-Informed Neural Network (PINN) fails to capture the multiscale nature of the problem, hence justifies the need to use Asymptotic-Preserving Neural Networks (APNNs). We show that not all classical AP formulations are fit for the neural network approach. We construct a micro-macro decomposition based neural network, and also build in a mass conservation mechanism into the loss function, in order to capture the dynamic and multiscale nature of the solutions. Numerical examples are used to demonstrate the effectiveness of this APNNs.

References in corpus (5)

• Fourier Neural Operator for Parametric Partial Differential Equations
• An overview on deep learning-based approximation methods for partial differential equations
• Least-Squares ReLU Neural Network (LSNN) Method For Linear Advection-Reaction Equation
• MIM: A deep mixed residual method for solving high-order partial differential equations
• Multiscale and Nonlocal Learning for PDEs using Densely Connected RNNs