Learning Mesh-Based Simulation with Graph Networks

by   Tobias Pfaff, et al.

Mesh-based simulations are central to modeling complex physical systems in many disciplines across science and engineering. Mesh representations support powerful numerical integration methods and their resolution can be adapted to strike favorable trade-offs between accuracy and efficiency. However, high-dimensional scientific simulations are very expensive to run, and solvers and parameters must often be tuned individually to each system studied. Here we introduce MeshGraphNets, a framework for learning mesh-based simulations using graph neural networks. Our model can be trained to pass messages on a mesh graph and to adapt the mesh discretization during forward simulation. Our results show it can accurately predict the dynamics of a wide range of physical systems, including aerodynamics, structural mechanics, and cloth. The model's adaptivity supports learning resolution-independent dynamics and can scale to more complex state spaces at test time. Our method is also highly efficient, running 1-2 orders of magnitude faster than the simulation on which it is trained. Our approach broadens the range of problems on which neural network simulators can operate and promises to improve the efficiency of complex, scientific modeling tasks.


page 2

page 3

page 6

page 12

page 13


Towards Fast Simulation of Environmental Fluid Mechanics with Multi-Scale Graph Neural Networks

Numerical simulators are essential tools in the study of natural fluid-s...

Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems

Simulations of complex physical systems are typically realized by discre...

Simulating Continuum Mechanics with Multi-Scale Graph Neural Networks

Continuum mechanics simulators, numerically solving one or more partial ...

Predicting Physics in Mesh-reduced Space with Temporal Attention

Graph-based next-step prediction models have recently been very successf...

Accurately Solving Physical Systems with Graph Learning

Iterative solvers are widely used to accurately simulate physical system...

Error Analysis for Quadtree-Type Mesh-Coarsening Algorithms Adapted to Pixelized Heterogeneous Microstructures

Pixel- and voxel-based representations of microstructures obtained from ...

Accelerating Numerical Solvers for Large-Scale Simulation of Dynamical System via NeurVec

Ensemble-based large-scale simulation of dynamical systems is essential ...