peterdsharpe/NeuralFoil
NeuralFoil is a practical airfoil aerodynamics analysis tool using physics-informed machine learning, exposed to end-users in pure Python/NumPy.
Trained on tens of millions of XFoil simulations, NeuralFoil provides 8 model variants trading accuracy for speed, with vectorized evaluation across angle-of-attack and Reynolds number. The hybrid architecture embeds physics-based invariants and includes an `analysis_confidence` metric to flag out-of-distribution predictions, enabling robust design optimization. It integrates seamlessly with AeroSandbox for extended capabilities (compressibility, post-stall behavior, control surfaces) while remaining a standalone NumPy runtime with <500 lines of user-facing code.
383 stars and 11,336 monthly downloads. Available on PyPI.
Stars
383
Forks
51
Language
Python
License
MIT
Category
Last pushed
Oct 17, 2025
Monthly downloads
11,336
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/peterdsharpe/NeuralFoil"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
tum-pbs/PhiFlow
A differentiable PDE solving framework for machine learning
pdebench/PDEBench
PDEBench: An Extensive Benchmark for Scientific Machine Learning
ArnauMiro/pyLowOrder
High performance parallel reduced order Modelling library
lettucecfd/lettuce
Computational Fluid Dynamics based on PyTorch and the Lattice Boltzmann Method
AI4Science-WestlakeU/RealPDEBench
[ICLR26 Oral] RealPDEBench: A Benchmark for Complex Physical Systems with Paired Real-World and...