About Our Project

In the 1940s, researchers discovered that radar could detect the position and movements of birds and other flying creatures such as insects. With this discovery, the field of radar ornithology was born. Researchers used this technique to the best of their ability with whatever data was available to them. The real breakthrough came in the 1990s when the United States began replacing its WSR57 weather surveillance radars with WSR-88D Weather Surveillance Radar 1988 Doppler. The WSR-88D or NEXRAD NExt Generation RADar system provided freely available radar data to researchers that covered a broad geospatial range.

By far, one of the most important aspects of the new system was the addition of a Doppler component to supplement the reflectivity data. Doppler data allowed researchers to look at bird migration in a new and exciting way. Large clusters of migrating birds could be observed approaching and descending at stopover points where they would rest until they began the next leg of their journey.

One of NEXRAD's greatest strengths has also been a significant obstacle for researchers studying bird migration; with 154 radar stations, each producing hundreds of volume scans per day, the amount of data to sort through is staggering. The real problem is that classifying birds in radar scans currently requires a skilled technician who has been trained in identifying the tell-tale signs that distinguish biological echoes from non-biological echoes. Consequently, the task of plotting a specific migration over any significant amount of space and time quickly becomes a difficult and resource intensive problem.

Montana State University in collaboration with the Northern Rocky Mountain Science Center is currently investigating approaches to this problem that leverage the power of machine learning techniques to automate the process of echo classification. We are currently focusing on classification using neural networks.