Bats play crucial ecological roles, and provide valuable ecosystem services, yet many populations face serious threats from various ecological disturbances. The North American Bat Monitoring Program (NABat) aims to assess status and trends of bat populations, while developing innovative and community-driven conservation solutions using its unique data and technology infrastructure. To support scalability and transparency in the NABat acoustic data pipeline, we developed a fully-automated, machine-learning algorithm. This codebase was used to develop V1.0 of our automated machine-learning system for detecting and classifying bat calls in ultrasonic recordings. This system performs three major functions:
Processing raw audio recording files, extracting bat pulses, and creating spectrogram images of detected pulses.
Iteratively training a deep-learning artificial network to create an algorithm that classifies bat pulses to species.
Validating and evaluating the classification algorithm's classification performance on holdback data.
|Title||North American Bat Monitoring Program: NABat Acoustic ML, Version 1.0.1|
|Authors||Gotthold Benjamin, Khalighifar Ali, Straw Bethany R, Reichert Brian E|
|Product Type||Software Release|
|Record Source||USGS Digital Object Identifier Catalog|
|USGS Organization||Fort Collins Science Center|