MistNet: Measuring historical bird migration in the US using archived weather radar data and convolutional neural networks

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 M ist N et , a deep convolutional neural network to discriminate precipitation from biology in radar scans. Unlike prior machine learning approaches, M ist N et makes fine‐scaled predictions and can collect biological information from radar scans that also contain precipitation. M ist N et 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 M ist N et using abundant noisy labels obtained from dual polarization radar data. In historical and contemporary WSR‐88D data, M ist N et 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, M ist N et retains 15% more biomass than traditional whole‐scan approaches to screening. M ist N et 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. M ist N et can enable large‐scale, long‐term, and reproducible measurements of whole migration systems.