Skip to content

Dataset · neashton

CFD simulation data for automotive aerodynamics

neashton/windsorml

High-accuracy aerodynamic calculations for 355 body geometry variants to train ML models.

What's inside

A machine learning dataset in external automotive aerodynamics by an NVIDIA author. It contains 355 Windsor body geometry variants with high-fidelity computational fluid dynamics (CFD) results. Metadata indicates image modality and a size from 100k to 1M records.

What you can do with it

  • Training ML surrogates for fast prediction of aerodynamic characteristics
  • Testing physics modeling models in the automotive industry
Size
100K–1M rows
Downloads this month
3.1M
Likes
7

How to load it

from datasets import load_dataset

ds = load_dataset("neashton/windsorml")