Advanced

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

Rydell, Jens LU ; Nyman, Stefan; Eklöf, Johan; Jones, Gareth A. and Russo, Danilo (2017) In Ecological Indicators 78. p.416-420
Abstract

Echolocating bats are surveyed and studied acoustically with bat detectors routinely and worldwide, yet identification of species from calls often remains ambiguous or impossible due to intraspecific call variation and/or interspecific overlap in call design. To overcome such difficulties and to reduce workload, automated classifiers of echolocation calls have become popular, but their performance has not been tested sufficiently in the field. We examined the absolute performance of two commercially available programs (SonoChiro and Kaleidoscope) and one freeware package (BatClassify). We recorded noise from rain and calls of seven common bat species with Pettersson real-time full spectrum detectors in Sweden. The programs could always... (More)

Echolocating bats are surveyed and studied acoustically with bat detectors routinely and worldwide, yet identification of species from calls often remains ambiguous or impossible due to intraspecific call variation and/or interspecific overlap in call design. To overcome such difficulties and to reduce workload, automated classifiers of echolocation calls have become popular, but their performance has not been tested sufficiently in the field. We examined the absolute performance of two commercially available programs (SonoChiro and Kaleidoscope) and one freeware package (BatClassify). We recorded noise from rain and calls of seven common bat species with Pettersson real-time full spectrum detectors in Sweden. The programs could always (100%) distinguish rain from bat calls, usually (68–100%) identify bats to group (Nyctalus/Vespertilio/Eptesicus, Pipistrellus, Myotis, Plecotus, Barbastella) and usually (83–99%) recognize typical calls of some species whose echolocation pulses are structurally distinct (Pipistrellus pygmaeus, Barbastella barbastellus). Species with less characteristic echolocation calls were not identified reliably, including Vespertilio murinus (16–26%), Myotis spp. (4–93%) and Plecotus auritus (0–89%). All programs showed major although different shortcomings and the often poor performance raising serious concerns about the use of automated classifiers for identification to species level in research and surveys. We highlight the importance of validating output from automated classifiers, and restricting their use to specific situations where identification can be made with high confidence. For comparison we also present the result of a manual identification test on a random subset of the files used to test the programs. It showed a higher classification success but performances were still low for more problematic taxa.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Biosonar, Methodology, Software, Species identification, Ultrasound
in
Ecological Indicators
volume
78
pages
5 pages
publisher
Elsevier
external identifiers
  • scopus:85016419173
  • wos:000406435900043
ISSN
1470-160X
DOI
10.1016/j.ecolind.2017.03.023
language
English
LU publication?
yes
id
2db131c4-85b3-4e1a-8d52-35344299da2a
date added to LUP
2017-04-11 08:43:26
date last changed
2018-01-14 04:31:36
@article{2db131c4-85b3-4e1a-8d52-35344299da2a,
  abstract     = {<p>Echolocating bats are surveyed and studied acoustically with bat detectors routinely and worldwide, yet identification of species from calls often remains ambiguous or impossible due to intraspecific call variation and/or interspecific overlap in call design. To overcome such difficulties and to reduce workload, automated classifiers of echolocation calls have become popular, but their performance has not been tested sufficiently in the field. We examined the absolute performance of two commercially available programs (SonoChiro and Kaleidoscope) and one freeware package (BatClassify). We recorded noise from rain and calls of seven common bat species with Pettersson real-time full spectrum detectors in Sweden. The programs could always (100%) distinguish rain from bat calls, usually (68–100%) identify bats to group (Nyctalus/Vespertilio/Eptesicus, Pipistrellus, Myotis, Plecotus, Barbastella) and usually (83–99%) recognize typical calls of some species whose echolocation pulses are structurally distinct (Pipistrellus pygmaeus, Barbastella barbastellus). Species with less characteristic echolocation calls were not identified reliably, including Vespertilio murinus (16–26%), Myotis spp. (4–93%) and Plecotus auritus (0–89%). All programs showed major although different shortcomings and the often poor performance raising serious concerns about the use of automated classifiers for identification to species level in research and surveys. We highlight the importance of validating output from automated classifiers, and restricting their use to specific situations where identification can be made with high confidence. For comparison we also present the result of a manual identification test on a random subset of the files used to test the programs. It showed a higher classification success but performances were still low for more problematic taxa.</p>},
  author       = {Rydell, Jens and Nyman, Stefan and Eklöf, Johan and Jones, Gareth A. and Russo, Danilo},
  issn         = {1470-160X},
  keyword      = {Biosonar,Methodology,Software,Species identification,Ultrasound},
  language     = {eng},
  month        = {07},
  pages        = {416--420},
  publisher    = {Elsevier},
  series       = {Ecological Indicators},
  title        = {Testing the performances of automated identification of bat echolocation calls : A request for prudence},
  url          = {http://dx.doi.org/10.1016/j.ecolind.2017.03.023},
  volume       = {78},
  year         = {2017},
}