NeuralOperator
Published 2021 | Version v2
Dataset Open

Navier-Stokes Dataset

Authors/Creators

  • 1. ROR icon California Institute of Technology
  • 2. ROR icon Nvidia (United States)

Contributors

Data collector:

  • 1. California Institute of Technology
  • 2. ROR icon Nvidia (United States)

Description

This dataset contains input-output pairs of PyTorch tensors that represent the time evolution of a fluid which flows according to the 2-d incompressible Navier-Stokes equations with Reynolds number 500. The data was originally generated at 1024x1024 resolution by a classical solver.

Files

Files (16.8 GB)

Name Size
md5:8b5c239a215e5e9ff0863fed2e8adcdf
15.4 GB Download
md5:70a389207ac93935d5ff3d4289d43581
1.5 GB Download

Additional details

Related works

Is part of
Preprint: arXiv:2310.00120 (arXiv)

Software

Repository URL
https://github.com/neuraloperator/neuraloperator
Programming language
Python
Development Status
Active