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 accuracy of classifying basic behavior 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.
Sixty-five miles long and more than 700 miles of shoreline make up an ambitious amount of water for scientists to monitor. Yet dozens of scientists over dozens of years have done just that. As a result, today the water quality in Lake Mead is high. Compared to water at other reservoirs across the nation. Lake Mead ranks in the category of "highest" for recreation and aquatic health. Keeping clean the water of Lake Mead is not a simple task, by any measure. On the one hand, the greatest volume of water entering the lake is nearly pristine snowmelt flowing from high in the western Rocky Mountains into the Colorado River. But on the other hand, parts of Lake Mead are the repository for 190 million gallons a day of highly treated wastewater from nearly 2 million people and population continues to increase. Former chemical manufacturing sites have left a legacy of pollution of banned substances like DDT and PCBs. A clean Lake Mead is crucial-for the irrigation of two million acres of crops.-for swimming, and other water-based recreation-and drinking water for 25 million people. Water quality here is so important Lake Mead has become one of the most studied bodies of water in the U.S. Scientists from a broad mix of agencies are focused on researching its water. Michael Rosen: There are scientists from all over the US who are working on this project. Biologists, hydrologists, eco-toxicologists, chemists all contributing their data to this interpretive work. Todd Tietjen: The benefit of collaboration between the various state, local, federal agencies and SNWA has facilitated the analysis of data for all of us. Kent Turner: There's been a tremendous amount of monitoring and research conducted by various agencies that provided an opportunity to develop a partnership and coordinate some of that research to identify where those gaps were and what might be a holistic picture for the current status and condition ecologically of Lake's Mead and Mohave. Michael Rosen: It's really important that we all collaborate together and I think everybody realizes that. Narrator: A new report dubbed " The Lake Mead Circular" brings the science together into one document for the public, managers and scientists.
"At, I think, eight or nine study sites we say declines between 30 and 50 percent." [KN, 9:45] : (voiceover) 8. CU of scientist rummaging around in the dirt. She or he finds an egg, moves dirt from around it and very gently lifts it up. [B-roll X-rays, 27:37] Larry LaPre "The tortoise has started having severe population declines in about 1989...." [LL1, 1:12] : (voiceover) 9. Tilt down from electrical tower to see three small tortoise carcasses with shells with holes pecked in. [DVD3, :05+] Becky Jones: "... very few of the small tortoises survive. There's about a 95% mortality rate within the first five years." [BJ1, 15:04] (voiceover) 10. Closeup of drawing blood from a tortoise. [Ft. Irwin blood draw, 11:31] Ken Nussear "We're seeing declining populations due to a variety of factors. Not just disease : (voiceover) not just predation, not just habitat loss but I think a mix of all those things 11. Closeup of vials going into holes in a centrifuge. [Ft. Irwin blood draw, 16:33]
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.