Generalization capabilities of MeshGraphNets to unseen geometries for fluid dynamics

Robin Schmöcker, Alexander Henkes, Julian Roth, Thomas Wick
8/12/2024
cs.LGcs.AImath.NA

No official code found. Best implementation: codebro634/modulus (25 stars, Apache-2.0, last commit 2024-06-06).

Abstract

This works investigates the generalization capabilities of MeshGraphNets (MGN) [Pfaff et al. Learning Mesh-Based Simulation with Graph Networks. ICML 2021] to unseen geometries for fluid dynamics, e.g. predicting the flow around a new obstacle that was not part of the training data. For this purpose, we create a new benchmark dataset for data-driven computational fluid dynamics (CFD) which extends DeepMind's flow around a cylinder dataset by including different shapes and multiple objects. We then use this new dataset to extend the generalization experiments conducted by DeepMind on MGNs by testing how well an MGN can generalize to different shapes. In our numerical tests, we show that MGNs can sometimes generalize well to various shapes by training on a dataset of one obstacle shape and testing on a dataset of another obstacle shape.

View on arXivView PDF

Code Implementations(1)

codebro634/modulusCommunity100%
Apache-2.0

Code for the Master's thesis: "Evaluation and improvements to Mesh Graph Nets for Computational Fluid Dynamics Simulations" which is built on the open-source deep-learning framework modulus by NVIDIA.

250Shell, PythonJan 4, 20242 years agoApache-2.0

Similar Papers

Scientific Computing Algorithms to Learn Enhanced Scalable Surrogates for Mesh Physics

87% match2023

Flow Matching and Diffusion Models via PointNet for Generating Fluid Fields on Irregular Geometries

84% match2026

Finite Volume Features, Global Geometry Representations, and Residual Training for Deep Learning-based CFD Simulation

83% match1 repo52026

MeshMask: Physics-Based Simulations with Masked Graph Neural Networks

83% match1 repo522025

Physics-informed MeshGraphNets (PI-MGNs): Neural finite element solvers for non-stationary and nonlinear simulations on arbitrary meshes

82% match2024

Generalizable data-driven turbulence closure modeling on unstructured grids with differentiable physics

82% match2023

Cite this paper

@article{schmcker2024generalization,
  title  = {Generalization capabilities of MeshGraphNets to unseen geometries for fluid dynamics},
  author = {Robin Schmöcker and Alexander Henkes and Julian Roth and Thomas Wick},
  year   = {2024},
  eprint = {2408.06101},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.06101v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.06101.svg)](https://codeofpaper.com/paper/2408.06101)

Discussion