Learning the Solution Operator of Boundary Value Problems using Graph Neural Networks

by   Winfried Lötzsch, et al.

As an alternative to classical numerical solvers for partial differential equations (PDEs) subject to boundary value constraints, there has been a surge of interest in investigating neural networks that can solve such problems efficiently. In this work, we design a general solution operator for two different time-independent PDEs using graph neural networks (GNNs) and spectral graph convolutions. We train the networks on simulated data from a finite elements solver on a variety of shapes and inhomogeneities. In contrast to previous works, we focus on the ability of the trained operator to generalize to previously unseen scenarios. Specifically, we test generalization to meshes with different shapes and superposition of solutions for a different number of inhomogeneities. We find that training on a diverse dataset with lots of variation in the finite element meshes is a key ingredient for achieving good generalization results in all cases. With this, we believe that GNNs can be used to learn solution operators that generalize over a range of properties and produce solutions much faster than a generic solver. Our dataset, which we make publicly available, can be used and extended to verify the robustness of these models under varying conditions.


page 5

page 8


Physics-Embedded Neural Networks: E(n)-Equivariant Graph Neural PDE Solvers

Graph neural network (GNN) is a promising approach to learning and predi...

Deep Learning-based surrogate models for parametrized PDEs: handling geometric variability through graph neural networks

Mesh-based simulations play a key role when modeling complex physical sy...

Multipole Graph Neural Operator for Parametric Partial Differential Equations

One of the main challenges in using deep learning-based methods for simu...

RBF-MGN:Solving spatiotemporal PDEs with Physics-informed Graph Neural Network

Physics-informed neural networks (PINNs) have lately received significan...

Boundary integrated neural networks (BINNs) for 2D elastostatic and piezoelectric problems: Theory and MATLAB code

In this paper, we make the first attempt to apply the boundary integrate...

Domain independent post-processing with graph U-nets: Applications to Electrical Impedance Tomographic Imaging

Reconstruction of tomographic images from boundary measurements requires...

Training Deep Surrogate Models with Large Scale Online Learning

The spatiotemporal resolution of Partial Differential Equations (PDEs) p...

Please sign up or login with your details

Forgot password? Click here to reset