Summary & Purpose

The accelerometer data collected and uploaded here is for the publication titled " Improved Supervised Classification of Accelerometry Data to Distinguish Behaviors of Soaring Birds". Soaring birds can balance the energetic costs of movement by switching between flapping, soaring and gliding flight. Accelerometers can allow quantification of flight behavior and thus a context to interpret these energetic costs. However, models to interpret accelerometry data are still being developed, rarely trained with supervised datasets, and difficult to apply. We collected accelerometry data at 140Hz from a trained golden eagle (Aquila chrysaetos) whose flight we recorded with video that we used to characterize behavior. We applied two forms of supervised classifications, random forest (RF) models and K-nearest neighbor (KNN) models. The KNN model was substantially easier to implement than the RF approach but both were highly accurate in classifying basic behaviors such as flapping (85.5% and 83.6% accurate, respectively), soaring (92.8% and 87.6%) and sitting (84.1% and 88.9%) with overall accuracies of 86.6% and 92.3% respectively. More detailed classification schemes, with specific behaviors such as banking and straight flights were well classified only by the KNN model (91.24% accurate; RF = 61.64% accurate). The RF model maintained its classification accuracy of basic behaviors at sampling frequencies as low as 10Hz, the KNN at sampling frequencies as low as 20Hz. Classification of accelerometer data collected from free ranging birds demonstrated a strong dependence of predicted behavior on the type of classification model used. Our analyses demonstrate the consequence of different approaches to classification of accelerometry data, the potential to optimize classification algorithms with validated flight behaviors to improve classification accuracy, ideal sampling frequencies for different classification algorithms, and a number of ways to improve commonly used analytical techniques and best practices for classification of accelerometry data.

Date of Publication or Submission



Funding Citation

This research was funded by the U.S. Bureau of Land Management IAA# L14PG00265 to Todd Katzner.

Single Dataset or Series?


Data Format


Data Attributes

We collected two types of accelerometry data from golden eagles, (1) those from a trained eagle whose flight behaviors we could observe and record on video and (2) those from wild eagles we could not observe. We outfitted the birds with a proprietary GPS and tri-axial accelerometry logging device custom designed by Cellular Tracking Technologies, LLC (CTT, Rio Grande, NJ). When operating, the logger collected accelerometry data at ~140Hz (measurements per second) and stored them in on-board flash memory. Those data were then manually downloaded and parsed as a .csv file. Each data file contains acceleration data in three planes (x, y and z axis), date and time stamps.

Privacy and Confidentiality Statement

Boise State University is explicitly compliant with federal and state laws surrounding data privacy including the protection of personal financial information through the Gramm-Leach-Bliley Act, personal medical information through HIPAA, HITECH and other regulations. All human subject data (e.g., surveys) has been collected and managed only by personnel with adequate human subject protection certification. The trained eagle was flown under falconry permits from the state of California to T. Suffredini and with consultation from permitting biologists in USFWS R8 and California Department of Fish and Wildlife. The wild eagles were flown under Animal Care and Use protocols authorized by West Virginia University and were captured and tagged under federal and state permits to T. Katzner.

Use Restrictions

Users should notify us and include us as co-authors on publications resulting from our data. We thank the Cattani family for allowing us access to their land to conduct the eagle flights, S. Poessel for assisting in data collection, Trish Miller of West Virginia University, Jeff Cooper of Virginia Department of Game and Inland Fisheries, Eric Soehren of Alabama Department of Conservation and Natural Resources, and David Hanni of Tennessee Wildlife Resources Agency for allowing units on wild eagles to have their duty cycles changed to collect accelerometer data. Any use of trade, product, or firm names is for descriptive purposes only and does not imply endorsement by the U.S. Government.