MistNet: Measuring historical bird migration in the US using archived weather radar data and convolutional neural networks
Authors:
- Tsung‐Yu LinTLTsung‐Yu Lin
- Kevin WinnerKWKevin Winner
- Garrett BernsteinGBGarrett Bernstein
- Abhay MittalAMAbhay Mittal
- Adriaan M. DokterADAdriaan M. Dokter
- Kyle G. HortonKHKyle G. Horton
- Cecilia NilssonCNCecilia Nilsson
- Benjamin M. Van DorenBDBenjamin M. Van Doren
- Andrew FarnsworthAFAndrew Farnsworth
- Frank A. La SorteFSFrank A. La Sorte
- Subhransu MajiSMSubhransu Maji
- Daniel SheldonDSDaniel Sheldon
- 27 August 2019
- journal article
- research article
- Published by Wiley in Methods in Ecology and Evolution
- Vol. 10 (11) , 1908-1922
Abstract
Large networks of weather radars are comprehensive instruments for studying bird migration. For example, the US WSR‐88D network covers the entire continental US and has archived data since the 1990s. The data can quantify both broad and fine‐scale bird movements to address a range of migration ecology questions. However, the problem of automatically discriminating precipitation from biology has significantly limited the ability to conduct biological analyses with historical radar data. We develop MistNet, a deep convolutional neural network to discriminate precipitation from biology in radar scans. Unlike prior machine learning approaches, MistNet makes fine‐scaled predictions and can collect biological information from radar scans that also contain precipitation. MistNet is based on neural networks for images, and includes several architecture components tailored to the unique characteristics of radar data. To avoid a massive human labelling effort, we train MistNet using abundant noisy labels obtained from dual polarization radar data. In historical and contemporary WSR‐88D data, MistNet identifies at least 95.9% of all biomass with a false discovery rate of 1.3%. Dual polarization training data and our radar‐specific architecture components are effective. By retaining biomass that co‐occurs with precipitation in a single radar scan, MistNet retains 15% more biomass than traditional whole‐scan approaches to screening. MistNet is fully automated and can be applied to datasets of millions of radar scans to produce fine‐grained predictions that enable a range of applications, from continent‐scale mapping to local analysis of airspace usage. Radar ornithology is advancing rapidly and leading to significant discoveries about continent‐scale patterns of bird movements. General‐purpose and empirically validated methods to quantify biological signals in radar data are essential to the future development of this field. MistNet can enable large‐scale, long‐term, and reproducible measurements of whole migration systems.Keywords
Funding Information
- US NSF Advances in Biological Informatics Program
- Edward W. Rose Postdoctoral Fellowship
This publication has 64 references indexed in Scilit:
- High Altitude Bird Migration at Temperate Latitudes: A Synoptic Perspective on Wind AssistancePLOS ONE, 2013
- Mapping Wintering Waterfowl Distributions Using Weather Surveillance RadarPLOS ONE, 2012
- Birds flee en mass from New Year’s Eve fireworksBehavioral Ecology, 2011
- Bird migration flight altitudes studied by a network of operational weather radarsJournal of The Royal Society Interface, 2010
- eBird: A citizen-based bird observation network in the biological sciencesBiological Conservation, 2009
- The Hydrometeor Classification Algorithm for the Polarimetric WSR-88D: Description and Application to an MCSWeather and Forecasting, 2009
- Observations of insects and birds with a polarimetric radarIEEE Transactions on Geoscience and Remote Sensing, 1998
- Detection of bird migration by centimetric radar—a cause of radar ‘angels’Proceedings of the Royal Society of London. B. Biological Sciences, 1958
- Detection of Birds by RadarNature, 1945
- ELECTRONICS AS A POSSIBLE AID IN THE STUDY OF BIRD FLIGHT AND MIGRATIONScience, 1945