M2N: Mesh Movement Networks for PDE SolversDownload PDF

Published: 31 Oct 2022, Last Modified: 12 Oct 2022NeurIPS 2022 AcceptReaders: Everyone
Keywords: Partial Differential Equation, Mesh Adaptation, Mesh Movement, Moving Mesh, r-Adaptation, Monge–Ampere, Deep Learning, Neural Network, Neural Spline, Graph Attention Network
Abstract: Numerical Partial Differential Equation (PDE) solvers often require discretizing the physical domain by using a mesh. Mesh movement methods provide the capability to improve the accuracy of the numerical solution without introducing extra computational burden to the PDE solver, by increasing mesh resolution where the solution is not well-resolved, whilst reducing unnecessary resolution elsewhere. However, sophisticated mesh movement methods, such as the Monge-Ampère method, generally require the solution of auxiliary equations. These solutions can be extremely expensive to compute when the mesh needs to be adapted frequently. In this paper, we propose to the best of our knowledge the first learning-based end-to-end mesh movement framework for PDE solvers. Key requirements of learning-based mesh movement methods are: alleviating mesh tangling, boundary consistency, and generalization to mesh with different resolutions. To achieve these goals, we introduce the neural spline model and the graph attention network (GAT) into our models respectively. While the Neural-Spline based model provides more flexibility for large mesh deformation, the GAT based model can handle domains with more complicated shapes and is better at performing delicate local deformation. We validate our methods on stationary and time-dependent, linear and non-linear equations, as well as regularly and irregularly shaped domains. Compared to the traditional Monge-Ampère method, our approach can greatly accelerate the mesh adaptation process by three to four orders of magnitude, whilst achieving comparable numerical error reduction.
TL;DR: The first learning-based end-to-end mesh movement framework that can greatly accelerate the mesh adaptation process by 3 to 4 orders of magnitude, whilst achieving comparable numerical error reduction to traditional sota methods.
Supplementary Material: pdf
11 Replies

Loading