$\Delta$-PINNs: physics-informed neural networks on complex geometries

Abstract

Physics-informed neural networks (PINNs) have demonstrated promise in solving forward and inverse problems involving partial differential equations. Despite recent progress on expanding the class of problems that can be tackled by PINNs, most of existing use-cases involve simple geometric domains. To date, there is no clear way to inform PINNs about the topology of the domain where the problem is being solved. In this work, we propose a novel positional encoding mechanism for PINNs based on the eigenfunctions of the Laplace-Beltrami operator. This technique allows to create an input space for the neural network that represents the geometry of a given object. We approximate the eigenfunctions as well as the operators involved in the partial differential equations with finite elements. We extensively test and compare the proposed methodology against traditional PINNs in complex shapes, such as a coil, a heat sink and a bunny, with different physics, such as the Eikonal equation and heat transfer. We also study the sensitivity of our method to the number of eigenfunctions used, as well as the discretization used for the eigenfunctions and the underlying operators. Our results show excellent agreement with the ground truth data in cases where traditional PINNs fail to produce a meaningful solution. We envision this new technique will expand the effectiveness of PINNs to more realistic applications.

26 pages, 14 figures

References in corpus (6)

• Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
• Efficient training of physics-informed neural networks via importance sampling
• Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
• WarpPINN: Cine-MR image registration with physics-informed neural networks
• A Physics-Informed Neural Network Framework For Partial Differential Equations on 3D Surfaces: Time-Dependent Problems
• Physics-informed neural networks to learn cardiac fiber orientation from multiple electroanatomical maps

Cited by in corpus (5)

• Residual-based Attention Physics-informed Neural Networks for Spatio-Temporal Ageing Assessment of Transformers Operated in Renewable Power Plants
• Learning thermoacoustic interactions in combustors using a physics-informed neural network
• Efficient PINNs via Multi-Head Unimodular Regularization of the Solutions Space
• Unfitted finite element interpolated neural networks
• Discovery of Quasi-Integrable Equations from traveling-wave data using the Physics-Informed Neural Networks