5.4 Automated Detection of Bird Roosts using NEXRAD Radar Data and Convolutional Neural Networks

Tuesday, 9 January 2018: 9:15 AM
Room 7 (ACC) (Austin, Texas)
Carmen Chilson, Univ. of Oklahoma, Norman, OK; and K. Avery, A. McGovern, E. Bridge, D. Sheldon, and J. F. Kelly

NEXRAD radars have proven to be an effective tool for detecting bird roosts but manually locating bird roosts in radar images is a time consuming process. It is important to study bird roosts because of their effect on crops, ecology, pathogens. This work focuses on applying machine learning to automatically determine whether each individual radar image contains at least one bird roost. We use a dataset of radar images that contain Purple Martin roosts and Tree swallow roosts in the Eastern half of the United States. We show that Convolutional Neural Networks (CNNs) are an effective method for automating the bird roost detection. CNNs have recently revolutionized image classification largely because CNNs capture spatial components of images. We hypothesized that these same principles can be applied to radar data. To further improve the accuracy of bird roost detection, machine learning techniques such as batch normalization and transfer learning are applied to the CNN. Our results show that CNNs are a promising approach for bird roost detection.
- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner