# Machine Learning to Predict Aerodynamic Stall

arXiv: https://arxiv.org/abs/2207.03424 · HTML: https://mlsanity.com/paper/2207.03424/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 20 references that are in the map.
- First posted on arXiv 7 Jul 2022.

## Builds on (most cited first, 3 of 3)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks](https://mlsanity.com/paper/1905.13166/) (2019)
- [Efficient collective swimming by harnessing vortices through deep reinforcement learning](https://mlsanity.com/paper/1802.02674/) (2018)

## Built on by (most cited first, 4 of 4)

- [A systematic dataset generation technique applied to data-driven automotive aerodynamics](https://mlsanity.com/paper/2408.07318/) (2024)
- [Generative Spatio-temporal GraphNet for Transonic Wing Pressure Distribution Forecasting](https://mlsanity.com/paper/2411.11592/) (2024)
- [Generative prediction of laser-induced rocket ignition with dynamic latent space representations](https://mlsanity.com/paper/2603.07525/) (2026)
- [Data-informed lifting line theory](https://mlsanity.com/paper/2603.29051/) (2026)

## Abstract (arXiv)

A convolutional autoencoder is trained using a database of airfoil aerodynamic simulations and assessed in terms of overall accuracy and interpretability. The goal is to predict the stall and to investigate the ability of the autoencoder to distinguish between the linear and non-linear response of the airfoil pressure distribution to changes in the angle of attack. After a sensitivity analysis on the learning infrastructure, we investigate the latent space identified by the autoencoder targeting extreme compression rates, i.e. very low-dimensional reconstructions. We also propose a strategy to use the decoder to generate new synthetic airfoil geometries and aerodynamic solutions by interpolation and extrapolation in the latent representation learned by the autoencoder.