NsCircle datasets from "Multi-scale rotation-equivariant graph neural networks for unsteady Eulerian fluid dynamics"

Datasets with the simulations of the incompressible flow around an elliptical as described by the incompressible Navier-Stokes equations. These simulations were used to train and test the MuS-GNN models in the paper:
    Multi-scale rotation-equivariant graph neural networks for
    unsteady Eulerian fluid dynamics (https://doi.org/10.1063/5.0097679)

The datasets are:
  - train/NsEllipse
  - test/NsEllipseLowRe
  - test/NsEllipseHighRe
  - test/NsEllipseThin
  - test/NsEllipseThick
  - test/NsEllipseNarrow
  - test/NsEllipseWide
  - test/NsEllipseAoA

To cite these datasets, use the following reference:

Mario Lino, Stathi Fotiadis, Anil A. Bharath, and Chris Cantwell. "Multi-scale rotation-equivariant graph neural networks for unsteady Eulerian fluid dynamics". Physics of Fluids, 34 (2022).

@article{lino2022multi,
    author = {Lino, Mario and Fotiadis, Stathi and Bharath, Anil A. and Cantwell, Chris},
    title = {{Multi-scale rotation-equivariant graph neural networks for unsteady Eulerian fluid dynamics}},
    journal = {Physics of Fluids},
    volume = {34},
    year = {2022},
    url = {https://doi.org/10.1063/5.0097679},
}