# Seeing the Wind: Visual Wind Speed Prediction with a Coupled Convolutional and Recurrent Neural Network

arXiv: https://arxiv.org/abs/1905.13290 · HTML: https://mlsanity.com/paper/1905.13290/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2019.

## Built on by (most cited first, 7 of 7)

- [The transformative potential of machine learning for experiments in fluid mechanics](https://mlsanity.com/paper/2303.15832/) (2023)
- [Self-Supervised Keypoint Discovery in Behavioral Videos](https://mlsanity.com/paper/2112.05121/) (2021)
- [SDWPF: A Dataset for Spatial Dynamic Wind Power Forecasting Challenge at KDD Cup 2022](https://mlsanity.com/paper/2208.04360/) (2022)
- [Seeing the Wind from a Falling Leaf](https://mlsanity.com/paper/2512.00762/) (2025)
- [DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics](https://mlsanity.com/paper/2603.09668/) (2026)
- [VS-LLM: Visual-Semantic Depression Assessment based on LLM for Drawing Projection Test](https://mlsanity.com/paper/2508.05299/) (2025)
- [Visual anemometry of natural vegetation from their leaf motion](https://mlsanity.com/paper/2504.10584/) (2025)

## Abstract (arXiv)

Wind energy resource quantification, air pollution monitoring, and weather forecasting all rely on rapid, accurate measurement of local wind conditions. Visual observations of the effects of wind---the swaying of trees and flapping of flags, for example---encode information regarding local wind conditions that can potentially be leveraged for visual anemometry that is inexpensive and ubiquitous. Here, we demonstrate a coupled convolutional neural network and recurrent neural network architecture that extracts the wind speed encoded in visually recorded flow-structure interactions of a flag and tree in naturally occurring wind. Predictions for wind speeds ranging from 0.75-11 m/s showed agreement with measurements from a cup anemometer on site, with a root-mean-squared error approaching the natural wind speed variability due to atmospheric turbulence. Generalizability of the network was demonstrated by successful prediction of wind speed based on recordings of other flags in the field and in a controlled wind tunnel test. Furthermore, physics-based scaling of the flapping dynamics accurately predicts the dependence of the network performance on the video frame rate and duration.