mlsanityData to 14 Oct 2026

NeuralFoil: An Airfoil Aerodynamics Analysis Tool Using Physics-Informed Machine Learning

arXiv 2503.16323 ↗First posted 20 Mar 2025physics.flu-dyn cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

NeuralFoil is an open-source Python-based tool for rapid aerodynamics analysis of airfoils, similar in purpose to XFoil. Speedups ranging from 8x to 1,000x over XFoil are demonstrated, after controlling for equivalent accuracy. NeuralFoil computes both global and local quantities (lift, drag, velocity distribution, etc.) over a broad input space, including: an 18-dimensional space of airfoil shapes, possibly including control deflections; a 360 degree range of angles of attack; Reynolds numbers from 102 to 1010; subsonic flows up to the transonic drag rise; and with varying turbulence parameters. Results match those of XFoil closely: the mean relative error of drag is 0.37% on simple cases, and remains as low as 2.0% on a test dataset with numerous post-stall and transitional cases. NeuralFoil facilitates gradient-based design optimization, due to its C^∞-continuous solutions, automatic-differentiation-compatibility, and bounded computational cost without non-convergence issues. NeuralFoil is a hybrid of physics-informed machine learning techniques and analytical models. Here, physics information includes symmetries that are structurally embedded into the model architecture, feature engineering using domain knowledge, and guaranteed extrapolation to known limit cases. This work also introduces a new approach for surrogate model uncertainty quantification that enables robust design optimization. This work discusses the methodology and performance of NeuralFoil with several case studies, including a practical airfoil design optimization study including both aerodynamic and non-aerodynamic constraints. Here, NeuralFoil optimization is able to produce airfoils nearly identical in performance and shape to expert-designed airfoils within seconds; these computationally-optimized airfoils provide a useful starting point for further expert refinement.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 5 of its 52 references that are in the map. First posted on arXiv 20 Mar 2025.

Builds on

5 of 52 references.

References · 5

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 772
  3. 2020How Neural Networks Extrapolate: From Feedforward to Graph Neural Networkscited by 222
  4. 2023Interpretable Machine Learning for Science with PySR and SymbolicRegression.jlcited by 54
  5. 2021PySensors: A Python Package for Sparse Sensor Placementcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 6.

11 papers.

  1. 2025Toward Autonomous Engineering Design: A Knowledge-Guided Multi-Agent Frameworkcited by 5
  2. 2025Transfer learning-enhanced deep reinforcement learning for aerodynamic airfoil optimisation subject to structural constraintscited by 4
  3. 2025Bayesian Optimization of a Lightweight and Accurate Neural Network for Aerodynamic Performance Predictioncited by 3
  4. 2025A Kernel-based Resource-efficient Neural Surrogate for Multi-fidelity Prediction of Aerodynamic Fieldcited by 3
  5. 2026In-Context Black-Box Optimization with Unreliable Feedbackcited by 2
  6. 2025GLOBE: Accurate and Generalizable PDE Surrogates using Domain-Inspired Architectures and Equivariancescited by 0
  7. 2026Neural-Surrogate Co-Design of Aerodynamic Shape and Controlcited by 0
  8. 2026Agentic Risk-Aware Set-Based Engineering Designcited by 0
  9. 2026AirfoilGen: A valid-by-construction and performance-aware latent diffusion model for airfoil generationcited by 0
  10. 2026CoFINN: Conservation Flux Informed Neural Networks for Physics Problems Governed by Conservation Lawscited by 0
  11. 2026Example-driven Parametrisations for Bayesian Shape Optimisationcited by 0