Spectrally Adapted Physics-Informed Neural Networks for Solving Unbounded Domain Problems
This addresses a computational bottleneck for researchers in physics and engineering dealing with unbounded domain problems, though it is an incremental improvement over existing PINN methods.
The authors tackled solving partial differential equations (PDEs) on unbounded domains by combining adaptive spectral methods with physics-informed neural networks (PINNs), resulting in a method that efficiently approximates solutions where standard PINNs fail, as demonstrated through examples.
Solving analytically intractable partial differential equations (PDEs) that involve at least one variable defined on an unbounded domain arises in numerous physical applications. Accurately solving unbounded domain PDEs requires efficient numerical methods that can resolve the dependence of the PDE on the unbounded variable over at least several orders of magnitude. We propose a solution to such problems by combining two classes of numerical methods: (i) adaptive spectral methods and (ii) physics-informed neural networks (PINNs). The numerical approach that we develop takes advantage of the ability of physics-informed neural networks to easily implement high-order numerical schemes to efficiently solve PDEs and extrapolate numerical solutions at any point in space and time. We then show how recently introduced adaptive techniques for spectral methods can be integrated into PINN-based PDE solvers to obtain numerical solutions of unbounded domain problems that cannot be efficiently approximated by standard PINNs. Through a number of examples, we demonstrate the advantages of the proposed spectrally adapted PINNs in solving PDEs and estimating model parameters from noisy observations in unbounded domains.