Multilevel domain decomposition-based architectures for physics-informed neural networks

Abstract

Physics-informed neural networks (PINNs) are a powerful approach for solving problems involving differential equations, yet they often struggle to solve problems with high frequency and/or multi-scale solutions. Finite basis physics-informed neural networks (FBPINNs) improve the performance of PINNs in this regime by combining them with an overlapping domain decomposition approach. In this work, FBPINNs are extended by adding multiple levels of domain decompositions to their solution ansatz, inspired by classical multilevel Schwarz domain decomposition methods (DDMs). Analogous to typical tests for classical DDMs, we assess how the accuracy of PINNs, FBPINNs and multilevel FBPINNs scale with respect to computational effort and solution complexity by carrying out strong and weak scaling tests. Our numerical results show that the proposed multilevel FBPINNs consistently and significantly outperform PINNs across a range of problems with high frequency and multi-scale solutions. Furthermore, as expected in classical DDMs, we show that multilevel FBPINNs improve the accuracy of FBPINNs when using large numbers of subdomains by aiding global communication between subdomains.

42 pages, 12 figures

References in corpus (3)

• Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Flow over an espresso cup: Inferring 3D velocity and pressure fields from tomographic background oriented schlieren videos via physics-informed neural networks

Cited by in corpus (9)

• Exploring spectropolarimetric inversions using neural fields. Solar chromospheric magnetic field under the weak-field approximation
• An overlapping domain decomposition method for the solution of parametric elliptic problems via proper generalized decomposition
• A Practitioner's Guide to Kolmogorov-Arnold Networks
• An operator preconditioning perspective on training in physics-informed machine learning
• A Nonoverlapping Domain Decomposition Method for Extreme Learning Machines: Elliptic Problems
• An approximate Riemann solver approach in Physics-Informed Neural Networks for hyperbolic conservation laws
• A Neumann-Neumann Acceleration with Coarse Space for Domain Decomposition of Extreme Learning Machines
• Regime-Aware Time Weighting for Physics-Informed Neural Networks
• Neural semi-Lagrangian method for high-dimensional advection-diffusion problems