Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published August 22, 2023 | in press
Journal Article

Visual anemometry for physics-informed inference of wind

  • 1. ROR icon California Institute of Technology


Accurate measurements of atmospheric flows at metre-scale resolution are essential for many sustainability applications, including optimal design of wind and solar farms, navigation and control of air flows in the built environment, monitoring of environmental phenomena such as wildfires and air pollution dispersal, and data assimilation into weather and climate models. Measurement of the relevant multiscale wind flows is inherently challenged by the optical transparency of the wind. This Perspective article explores new ways in which physics can be leveraged to 'see' environmental flows non-intrusively, that is, without the need to place measurement instruments directly in the flows of interest. Specifically, although wind itself is transparent, its effect can be seen in the motion of objects embedded in the environment and subjected to wind — swaying trees and flapping flags are commonly encountered examples. We survey emerging efforts to accomplish visual anemometry, the task of quantitatively inferring local wind conditions on the basis of the physics of observed flow–structure interactions. Approaches based on first-principles physics as well as data-driven, machine learning methods will be described, and remaining obstacles to fully generalizable visual anemometry are discussed.

Copyright and License

© Springer Nature Limited 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.


The authors gratefully acknowledge seminal contributions from J.L. Cardona in development of several of the concepts presented in this Perspective article, as well as discussions with K. Bouman, J. Sun, Y. Yue and P. Perona at Caltech. Additional helpful discussions occurred in the CV4Ecology Summer Workshop, supported by the Caltech Resnick Sustainability Institute. Constructive feedback from the anonymous reviewers led to meaningful improvements to the presentation of the material in this manuscript. Funding was generously provided by the National Science Foundation (Grant CBET-2019712) and the Center for Autonomous Systems and Technologies at Caltech. Additional support from Heliogen is gratefully acknowledged.


All authors contributed to all aspects of the manuscript.

Conflict of Interest

The authors declare no competing interests.

Additional details

September 28, 2023
September 28, 2023