Automated classification of avian vocal activity using acoustic indices in regional and heterogeneous datasets

Abstract

Acoustic indices combined with clustering and classification approaches have been increasingly used to automate identification of the presence of vocalizing taxa or acoustic events of interest. While most studies using this approach standardize data collection and study design parameters at the project or study level, recent trends in ecological research are to investigate patterns at regional or continental scales. Large‐scale studies often require collaboration between research groups and integration of data from multiple sources to fulfil objectives, which can lead to variation in recording equipment and data collection protocols. Our objectives were to determine how analytical approaches and variation in data collection and processing that is typical of regional acoustic monitoring programmes influences accuracy when identifying vocal activity in breeding birds. We used data from three regional datasets in Northern Alberta, Northern British Columbia, and Southern and Central Yukon, Canada to investigate the effect of analytical framework, sample size, local species richness and data collection variables on classification accuracy. We found supervised classification approaches to be the most effective, with boosted regression trees identifying vocalizations of breeding birds in audio recordings with a 92.0% accuracy and easily able to accommodate variation in data collection and processing parameters. We also provide recommendations on effectively processing large and heterogeneous datasets including sufficient sample size, accommodating potentially confounding variables and selecting suitable model training data. The results presented in this study can help inform decisions in data collection, data processing, and study design and analysis, maximize performance and accuracy during analysis, and efficiently process large, heterogeneous acoustic datasets to answer questions at scales previously difficult to investigate.

Linking acoustic diversity to compositional and configurational heterogeneity in mosaic landscapes

“…While several indices are needed to reveal diel and seasonal soundscape patterns (Bradfer-Lawrence et al 2019), AIs have been shown to be often weakly correlated to biophony assessed independently because of signal masking by non-target sounds (Fairbrass et al 2017;Metcalf et al 2021). Moreover, a combination of indices is generally required to successfully predict biodiversity values (Towsey et al 2014;Buxton et al 2018;Yip et al 2021). Here, we modelled the responses of six AIs that are increasingly used as a standard analysis path to characterize spatial or temporal changes in acoustic biodiversity (Sueur et al 2014;Bradfer-Lawrence et al 2020).…”

“…Furthermore, there are still few studies exploring the potential change in the direction of effects between different biomes and habitats, because sampling biodiversity simultaneously on large geographical gradients without observer biases remains difficult. Recording the sound of biodiversity with autonomous devices is a promising way of limiting such observer biases in large-scale sampling schemes (Ross et al 2021;Yip et al 2021). However, few studies to date have investigated how more integrative biodiversity metrics such as multi-species acoustic indices could respond to landscape heterogeneity at wider scales (but see Fuller et al 2015;Dein and Rüdisser 2020;Dooley and Brown 2020).…”

“…Its largescale assessment has been strengthened in the recent years according to rapid technological developments in Passive Acoustic Monitoring (Bradfer-Lawrence et al 2019;Gibb et al 2019;Sugai et al 2020;Wood et al 2021). Passive Acoustic Monitoring (PAM) provides a holistic picture of biodiversity through the recording and analysis of intricate patterns of sound, especially at larger spatial scales (Krause 2008Drake et al 2021Ross et al 2021;Yip et al 2021). Not only biodiversitynotably breeding bird -surveys will benefit from the large-scale deployment of automated recorders, but this will give more insights on how bird song attractiveness is connected to human well-being and will help considering soundscape conservation as a cultural value (Ferraro et al 2020;Barbaro et al 2021;Morrison et al 2021).…”

Diversity Monitoring of Coexisting Birds in Urban Forests by Integrating Spectrograms and Object-Based Image Analysis

“…Techniques from machine learning and computational intelligence have been used in bird vocalization analysis [79,80]. In the present study, CART [81] was applied to construct accurate and reliable predictive models for syllable extraction.…”

Quantifying Firebrand Production and Transport Using the Acoustic Analysis of In-Fire Cameras

“…Recent advances in acoustic pattern recognition in the field of bioacoustics and soundscape ecology have greatly increased our ability to automate the identification of target signals or patterns in large volumes of data [30]. Automated recognition has successfully been used to identify a wide range of taxa in a variety of environments, including but not limited to birds [31], mammals [32], and amphibians [33] using a variety of methods such as spectrogram cross-correlation and analysis [34], machine learning [35], and classification of acoustic indices ( [36,37]). While these recognition approaches have typically been used to identify acousti-cally active animals, the same approaches can be applied to acoustically distinct abiotic sounds [38].…”