Advancing bird survey efforts through novel recorder technology and automated species identification

Abstract

Recent advances in acoustic recorder technology and automated species identification hold great promise for avian monitoring efforts. Assessing how these innovations compare to existing recorder models and traditional species identification techniques is vital to understanding their utility to researchers and managers. We carried out field trials in Monterey County, California, to compare bird detection among four acoustic recorder models (AudioMoth, Swift Recorder, and Wildlife Acoustics SM3BAT and SM Mini) and concurrent point counts, and to assess the ability of the artificial neural network BirdNET to correctly identify bird species from AudioMoth recordings. We found that the lowest-cost unit (AudioMoth) performed comparably to higher-cost units and that on average, species detections were higher for three of the five recorder models (range 9.8 to 14.0) than for point counts (12.8). In our assessment of BirdNET, we developed a subsetting process that enabled us to achieve a high rate of correctly identified species (96%). Using longer recordings from a single recorder model, BirdNET identified a mean of 8.5 verified species per recording and a mean of 16.4 verified species per location over a 5-day period (more than point counts conducted in similar habitats). We demonstrate that a combination of long recordings from low-cost recorders and a conservative method for subsetting automated identifications from BirdNET presents a process for sampling avian community composition with low misidentification rates and limited need for human vetting. These low-cost and automated tools may greatly improve efforts to survey bird communities and their ecosystems, and consequently, efforts to conserve threatened indigenous biodiversity.

Keywords

• acoustic monitoring
• aru
• audiomoth
• autoclassification
• birdnet
• birds
• point count
• species identification