Detecting and Tracking Communal Bird Roosts in Weather Radar Data
This provides biologists with comprehensive spatio-temporal data to study broad-scale habitat use and movements of communally roosting birds during the non-breeding season, addressing a domain-specific problem with incremental methodological improvements.
The paper tackles the problem of detecting and tracking communal bird roosts in weather radar data by developing a machine learning system that uses a latent variable model and EM algorithm to account for labeling variations, resulting in a significantly more accurate detector that identifies previously unknown roosting locations across the US.
The US weather radar archive holds detailed information about biological phenomena in the atmosphere over the last 20 years. Communally roosting birds congregate in large numbers at nighttime roosting locations, and their morning exodus from the roost is often visible as a distinctive pattern in radar images. This paper describes a machine learning system to detect and track roost signatures in weather radar data. A significant challenge is that labels were collected opportunistically from previous research studies and there are systematic differences in labeling style. We contribute a latent variable model and EM algorithm to learn a detection model together with models of labeling styles for individual annotators. By properly accounting for these variations we learn a significantly more accurate detector. The resulting system detects previously unknown roosting locations and provides comprehensive spatio-temporal data about roosts across the US. This data will provide biologists important information about the poorly understood phenomena of broad-scale habitat use and movements of communally roosting birds during the non-breeding season.