The Problem of Low Agreement among Automated Identification Programs for Acoustical Surveys of Bats

Lemen, Cliff A.; Freeman, Patricia W.; White, Jeremy A.; Andersen, Brett R.

doi:10.3398/064.075.0210

Cited by 55 publications

(55 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our results support the growing number of studies that caution on the use of auto‐id programs for bat echolocation calls (e.g., Lemen et al , Russo and Voigt , Rydell et al ). The quality of the calls used to construct call libraries is generally unknown, as is the type of habitat the calls were recorded in or what effect it may have on the species identified.…”

Section: Management Implicationssupporting

confidence: 87%

“…However, the accuracy of the software is subject to debate. When software packages such as Bat Call ID (Bat Call Identification; http://www.batcallid.com), EchoClass (Eric Britzke; http://www.fws.gov/midwest/Endangered/mammals/inba/surveys/inbaAcousticSoftware.html), Kaleidoscope Pro (Wildlife Acoustics; http://www.wildlifeacoustics.com), and SonoBat (Arcata; http://www.sonobat.com) were tested against large acoustic samples of unknown bat species, the packages agreed on species identification only 40% of the time (Lemen et al ). Multiple variables can be measured from a single bat call, so multivariate discriminant‐function analysis is a good approach when identifying echolocation calls (Russo and Voigt , Rydell et al ).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Acoustic Surveys for Bats are Improved by Taking Habitat Type into Account

Findlay

Barclay

2019

Wildl. Soc. Bull.

View full text Add to dashboard Cite

Passive monitoring of bat species via acoustics is a growing field and as a result there are various software programs available that allow for species identification. However, accuracy of these programs is variable and creating a local call library is essential when trying to identify acoustically similar species. In Dinosaur Provincial Park, Alberta, Canada, 3 Myotis species are difficult to distinguish acoustically. We created an echolocation call library from known Myotis evotis, M. lucifugus, and M. ciliolabrum flying in open spaces and near clutter to test whether or not recording in the bats' local habitat type improved call library quality and identification accuracy. Bat calls recorded within open spaces (coulees) differed from those recorded near cluttered spaces (tree edges) for M. ciliolabrum and M. lucifugus. Accuracy of species identification also increased when we used models based on bat calls recorded in cluttered habitats. Using a simple model with recordings from different habitat types within a study site, we were able to improve identification accuracy and model performance. © 2019 The Wildlife Society.

show abstract

Section: Management Implicationssupporting

confidence: 87%

mentioning

confidence: 99%

Acoustic Surveys for Bats are Improved by Taking Habitat Type into Account

Findlay

Barclay

2019

Wildl. Soc. Bull.

View full text Add to dashboard Cite

show abstract

“…Although the limitations of automated classification have been highlighted by showing that 4 different software packages identify calls of unknown bat species in different ways (Lemen et al, 2015), the reliability of identifying species of known identity remains little known. A first step is to test the performances of some popular software in the field under normal working conditions.…”

Section: Introductionmentioning

confidence: 99%

Testing the performances of automated identification of bat echolocation calls: A request for prudence

Rydell

Nyman

Eklöf

et al. 2017

Ecological Indicators

108

View full text Add to dashboard Cite

show abstract

“…Performance depends in part on extraneous sources of sound (e.g., other species' calls) and the overall noisiness of the environment (e.g., anthropogenic noise, wind, rain), as well as the acoustic structure of the vocalizations, which is important in the choice of algorithm (Brandes, 2008;Cragg, Burger, & Piatt, 2015;Priyadarshani, Marsland, & Castro, 2018;Salamon et al, 2016;Towsey, Planitz, Nantes, Wimmer, & Roe, 2012). Ultrasonic vocalizations are less subject to the masking effects of noise, however, reviews of commercially available bat call detection software suggest poor reliability (Lemen, Freeman, White, & Andersen, 2015;Russo & Voigt, 2016). For the frequencymodulated whistle of the currawong, Strepera graculina, they used hidden Markov models (40% recall; 100% precision; 90% accuracy), while for the pulsatile bellows of male koalas, they used binary template matching (75% recall; 75% precision; 95% accuracy).…”

Section: Challenges and Considerations For Bioacoustic Monitoring Pmentioning

confidence: 99%

Bioacoustic monitoring of animal vocal behavior for conservation

Teixeira

Maron

Rensburg

2019

Conservat Sci and Prac

View full text Add to dashboard Cite

The popularity of bioacoustics for threatened species monitoring has surged. Large volumes of acoustic data can be collected autonomously and remotely with minimal human effort. The approach is commonly used to detect cryptic species and, more recently, to estimate abundance or density. However, the potential for conservationrelevant information to be derived from acoustic signatures associated with particular behavior is less well-exploited. Animal vocal behavior can reveal important information about critical life history events. In this study, we argue that the overlap of the disciplines of bioacoustics, vocal communication, and conservation behavior-thus, "acoustic conservation behavior"-has much to offer threatened species monitoring.In particular, vocalizations can serve as indicators of behavioral states and contexts that provide insight into populations as it relates to their conservation. We explore the information available from monitoring species' vocalizations that relate to reproduction and recruitment, alarm and defense, and social behavior, and how this information could translate into potential conservation benefits. While there are still challenges to processing acoustic data, we conclude that acoustic conservation behavior may improve threatened species monitoring where vocalizations reveal behaviors that are informative for management and decision-making. K E Y W O R D Sbioacoustics, conservation behavior, monitoring, vocal behavior, vocalizations

show abstract

The Problem of Low Agreement among Automated Identification Programs for Acoustical Surveys of Bats

Cited by 55 publications

References 7 publications

Acoustic Surveys for Bats are Improved by Taking Habitat Type into Account

Acoustic Surveys for Bats are Improved by Taking Habitat Type into Account

Testing the performances of automated identification of bat echolocation calls: A request for prudence

Bioacoustic monitoring of animal vocal behavior for conservation

Contact Info

Product

Resources

About