README.md

metadata

title: 2d Predictor
emoji: 👀
colorFrom: indigo
colorTo: red
sdk: gradio
sdk_version: 6.0.1
app_file: app.py
pinned: false
license: mit
short_description: Web-app and APIs to get NeuralFoil predictions

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

NeuralFoil Airfoil Predictor (Hugging Face Space)

This Space wraps NeuralFoil in a Gradio UI.

It runs a NeuralFoil surrogate model to estimate airfoil aerodynamics (CL, CD, CM, transition locations, and an analysis confidence metric) for a single operating point.

NeuralFoil is a neural-network-based surrogate for XFoil.
Given an airfoil and operating conditions, it predicts aerodynamic coefficients and related quantities much faster than traditional CFD or XFoil.

This Space only wraps that functionality and does not train any models itself.

Features

• Airfoil definition

  • By name via AeroSandbox (UIUC / NACA-style names, e.g. naca4412, rae2822, clarky)
  • By .dat file upload (XFoil-style coordinate file)
  • numpy coordinates

• Operating point inputs

  • Angle of attack α [deg]
  • Reynolds number Re [-]
  • NeuralFoil model size (xxsmall … xxxlarge)

• Outputs

  • Lift coefficient CL
  • Drag coefficient CD
  • Moment coefficient CM
  • Transition locations: Top_Xtr, Bot_Xtr (if available)
  • analysis_confidence + a crude textual interpretation
  • Full raw NeuralFoil output JSON (for power users / debugging)

Running locally

Quick Start (if already set up)

./run.sh
# or
source venv/bin/activate && python app.py

First Time Setup

# 1. Create virtual environment
python3 -m venv venv

# 2. Activate virtual environment
source venv/bin/activate  # macOS/Linux
# or
venv\Scripts\activate     # Windows

# 3. Install dependencies
pip install --upgrade pip
pip install -r requirements.txt

# 4. Run the app
python app.py

The app will start on http://127.0.0.1:7860 (or next available port).

See SETUP.md for detailed setup instructions and troubleshooting.

License

• NeuralFoil itself is MIT-licensed (see its own repository for details).
• This Space is just a thin wrapper around NeuralFoil and AeroSandbox.

Citation

If you use NeuralFoil in your research, please cite: Both the tool itself (this repository), which includes the pre-print publication:

@misc{neuralfoil,
  author = {Peter Sharpe},
  title = {{NeuralFoil}: An airfoil aerodynamics analysis tool using physics-informed machine learning},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/peterdsharpe/NeuralFoil}},
}

And the author's PhD thesis, which has an extended chapter that serves as the primary long-form documentation for the tool:

@phdthesis{aerosandbox_phd_thesis,
   title = {Accelerating Practical Engineering Design Optimization with Computational Graph Transformations},
   author = {Sharpe, Peter D.},
   school = {Massachusetts Institute of Technology}, 
   year = {2024},
}