Abstract
The use of passive acoustic monitoring in wildlife ecology has increased dramatically in recent years as researchers take advantage of improvements in autonomous recording units and analytical methods. These technologies have allowed researchers to collect large quantities of acoustic data which must then be processed to extract meaningful information, e.g. target species detections. A persistent issue in acoustic monitoring is the challenge of efficiently automating the detection of species of interest, and deep learning has emerged as a powerful approach to accomplish this task. Here we report on the development and application of a deep convolutional neural network for the automated detection of 14 forest-adapted birds and mammals by classifying spectrogram images generated from short audio clips. The neural network performed well for most species, with precision exceeding 90% and recall exceeding 50% at high score thresholds, indicating high power to detect these species when they were present and vocally active, combined with a low proportion of false positives. We describe a multi-step workflow that integrates this neural network to efficiently process large volumes of audio data with a combination of automated detection and human review. This workflow reduces the necessary human effort by > 99% compared to full manual review of the data. As an optional component of this workflow, we developed a graphical interface for the neural network that can be run through RStudio using the Shiny package, creating a portable and user-friendly way for field biologists and managers to efficiently process audio data and detect these target species close to the point of collection and with minimal delays using consumer-grade computers.
Highlights
Artificial intelligence technologies are increasingly being applied to issues in ecological research and conservation
We present an original workflow designed for processing large amounts of audio data from passive acoustic monitoring for northern spotted owls and other forest-adapted bird and mammal species in the Pacific Northwest
We expanded on previous proof-of-concept work to train a CNN on 14 target species, resulting in higher performance compared to the network previously reported in Ruff et al (2020)
Summary
Artificial intelligence technologies are increasingly being applied to issues in ecological research and conservation. In the field of wildlife ecology, the use of artificial intelligence in combination with recent advances in survey techniques has enabled researchers to collect data on species occurrences at much broader spatial and temporal scales than were previously possible Passive monitoring methods such as camera traps and bioacoustics have greatly improved the capacity of researchers to survey for wildlife, but the resulting large datasets require substantial processing to extract useful information. Auto mated or semi-automated approaches can greatly reduce the amount of time and effort required to extract and classify detections of target an imals (Norouzzadeh et al, 2017; Willi et al, 2018) This allows researchers to proceed more quickly from data collection to analysis, generating insights on the underlying ecological processes in closer to real time and enabling more timely management responses to changes in the system
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
