VKI-LS59: 2D Turbine Cascade RANS Dataset under Geometric Variations (PLAID)

Provider
Safran (Michele Alessandro Bucci, Luca Saverio, Fabien Casenave et al.)
License
CC-BY-SA-4.0 (source)
Size
8 files
Format
Parquet (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/PLAID-datasets/VKI-LS59)
Access
Free and public. No account with the data provider is needed.
Category
Physics
Source
https://doi.org/10.5281/zenodo.14840512

About VKI-LS59: 2D Turbine Cascade RANS Dataset under Geometric Variations (PLAID)

VKI-LS59 is a 2D internal aerodynamics dataset of RANS solutions for geometric variations based on the VKI LS59 blade, published by Safran and collaborators (Bucci, Saverio, Casenave and others) as part of the PLAID benchmark collection for physics surrogate models. Inputs are two scalars and the geometry (with a signed distance field); outputs are seven fields and six scalars. Eight nested training sets of 8 to 671 samples and a 168-sample test set with withheld outputs are provided. The repository uses about 4.5 GB (measured 2026-11-14). Samples are PLAID objects whose meshes follow the CGNS standard; load with Hugging Face datasets and convert with the plaid library (plaid.bridges.huggingface_bridge), or turn meshes into Muscat meshes. Released on Zenodo by the authors under CC-BY-SA-4.0.

How to load this dataset in Python

from datasets import load_dataset
ds = load_dataset("PLAID-datasets/VKI-LS59")
print(ds)

Data structure

File types in sampled files: Parquet

Files

Example file: data/all_samples-00000-of-00006.parquet

Analyze this dataset without downloading it

On Scigantic, VKI-LS59: 2D Turbine Cascade RANS Dataset under Geometric Variations (PLAID) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Physics datasets