datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
NavierStokes-2DNavierStokes-2D-conditonednavier-stokes-dataset
Navier Stokes Dataset of Isotropic Turbulence in a periodic box
The dataset for tensor-to-tensor or trajectory-to-trajectory neural operators, generated from Navier-Stokes equations
to model the isotropic turbulence [1] such that the spectra satisfy the inverse cascade discovered by A.N. Kolmogorov [2].
[1]: McWilliams, J. C. (1984). The emergence of isolated coherent vortices in turbulent flow. Journal of Fluid Mechanics, 146, 21-43.
[2]: Kolmogorov, A. N. (1941). The local… See the full description on the dataset page: https://huggingface.co/datasets/scaomath/navier-stokes-dataset.PreGen-NavierStokes-2D
PreGen Navier-Stokes 2D Dataset
Paper | Project Page | Code
Dataset Description
This dataset accompanies the research paper Pre-Generating Multi-Difficulty PDE Data For Few-Shot Neural PDE Solvers (under review at ICLR 2026). It contains systematically generated 2D incompressible Navier-Stokes fluid flow simulations designed to study difficulty transfer in neural PDE solvers.The key insight: by pre-generating many low and medium difficulty examples and including them… See the full description on the dataset page: https://huggingface.co/datasets/sage-lab/PreGen-NavierStokes-2D.1D-Compressible-Navier-Stokesnavier-stokes-1e-5navier-stokes-2d-fno
Navier-Stokes 2D (ν = 1e-3)
Simulations of the 2D Navier-Stokes equation for a viscous, incompressible fluid in
vorticity form on the unit torus, following the Fourier Neural Operator (FNO) benchmark
of Li et al. (2021).
Each sample is the time evolution of the vorticity field w(x, y, t) on a periodic
64 × 64 grid over 20 time steps.
Intended use: this dataset is meant to be used for both training and testing /
evaluation of neural operators and PDE surrogate models. It is… See the full description on the dataset page: https://huggingface.co/datasets/abelsr1710/navier-stokes-2d-fno.navier-stokes-cylinder
Navier-Stokes Flow Around Cylinder Dataset
Dataset Description
This dataset contains computational fluid dynamics simulations of incompressible flow around a cylinder with varying viscosity parameters.
Dataset Summary
The Navier-Stokes Cylinder dataset provides numerical simulations of viscous fluid flow around a circular cylinder. The dataset includes velocity fields (x and y components) and pressure fields, making it ideal for fluid dynamics research… See the full description on the dataset page: https://huggingface.co/datasets/SISSAmathLab/navier-stokes-cylinder.navier-stokesnavier-stokes-singularity-simulation
Native Navier–Stokes simulation voxels
Lossless exports of velocity and manufactured forcing from Oliver's completed
AMReX / incflo experiment. The source has 280 saved states from exact rest
through t = 0.995, including an exactly quiescent interval through t = 0.55.
An explicitly labeled prototype may contain fewer states; each release's
manifest.json is authoritative about its coverage.
Layout and access
Each content-addressed releases/<manifest-hash-prefix>/… See the full description on the dataset page: https://huggingface.co/datasets/ccm/navier-stokes-singularity-simulation.navier-stokes-benchmark
Navier-Stokes Analytical Benchmark
A benchmark dataset of fluid dynamics problems with exact or semi-analytical solutions that target structural failure modes of SINDy and EDMD. Designed for evaluating deep-koopman-kan (Koopman-based lifting) and KANDy (equation discovery) pipelines.
Each problem class isolates a specific reason why sparse-regression (SINDy) and linear-Koopman (EDMD) methods provably fail on real Navier-Stokes flows. The latex_equation field serves as the… See the full description on the dataset page: https://huggingface.co/datasets/C3S2-Lab/navier-stokes-benchmark.navier_stokes_datasetsnavier-stokes-2d-fno
Navier-Stokes 2D (ν = 1e-3)
Simulations of the 2D Navier-Stokes equation for a viscous, incompressible fluid in
vorticity form on the unit torus, following the Fourier Neural Operator (FNO) benchmark
of Li et al. (2021).
Each sample is the time evolution of the vorticity field w(x, y, t) on a periodic
64 × 64 grid over 20 time steps.
Intended use: this dataset is meant to be used for both training and testing /
evaluation of neural operators and PDE surrogate models. It is… See the full description on the dataset page: https://huggingface.co/datasets/viper333qaq/navier-stokes-2d-fno.navier_stokes_res1024_Re10e5navier-stokes-dataset
Navier Stokes Dataset of Isotropic Turbulence in a periodic box
The dataset for tensor-to-tensor or trajectory-to-trajectory neural operators, generated from Navier-Stokes equations
to model the isotropic turbulence [1] such that the spectra satisfy the inverse cascade discovered by A.N. Kolmogorov [2].
[1]: McWilliams, J. C. (1984). The emergence of isolated coherent vortices in turbulent flow. Journal of Fluid Mechanics, 146, 21-43.
[2]: Kolmogorov, A. N. (1941). The local… See the full description on the dataset page: https://huggingface.co/datasets/introvoyz043/navier-stokes-dataset.hyper-navier-stokes-64-1000
Incompressible Navier Stokes 2D Dataset Summary
This is the primary dataset used in the ICLR 2025 paper Model-Agnostic Knowledge Guided Correction for Improved Neural Surrogate Rollout.
Please see https://github.com/scailab/HyPER for our code and instructions on training our models with this dataset.
navier-stokes-1e-4PreGen-NavierStokes-2D
PreGen Navier-Stokes 2D Dataset
Dataset Description
This dataset accompanies the research paper "Pre-Generating Multi-Difficulty PDE Data For Few-Shot Neural PDE Solvers" (under review at ICLR 2026). It contains systematically generated 2D incompressible Navier-Stokes fluid flow simulations designed to study difficulty transfer in neural PDE solvers.
The key insight: by pre-generating many low and medium difficulty examples and including them with a small number of hard… See the full description on the dataset page: https://huggingface.co/datasets/Ved100/PreGen-NavierStokes-2D.NavierStokes-2DNavier-Stokes-Pretraining