Artigo

Stronger together: Combining automated classifiers with manual post-validation optimizes the workload vs reliability trade-off of species identification in bat acoustic surveys

Owing to major technological advances, bioacoustics has become a burgeoning field in ecological research worldwide. Autonomous passive acoustic recorders are becoming widely used to monitor aerial insectivorous bats, and automatic classifiers have emerged to aid researchers in the daunting task of a...

ver descrição completa

Autor principal: López-Baucells, Adrià
Outros Autores: Torrent, Laura, Rocha, Ricardo, E.D. Bobrowiec, Paulo, Palmeirim, Jorge Manuel, Meyer, Christoph F.J.
Grau: Artigo
Idioma: English
Publicado em: Ecological Informatics 2020
Assuntos:
Accuracy Assessment
Algorithm
Bat
Bioacoustics
Echolocation
Survey Method
Trade-off
Amazonia
Brasil
Chiroptera
Acesso em linha: https://repositorio.inpa.gov.br/handle/1/16800
id oai:repositorio:1-16800
recordtype dspace
spelling oai:repositorio:1-16800 Stronger together: Combining automated classifiers with manual post-validation optimizes the workload vs reliability trade-off of species identification in bat acoustic surveys López-Baucells, Adrià Torrent, Laura Rocha, Ricardo E.D. Bobrowiec, Paulo Palmeirim, Jorge Manuel Meyer, Christoph F.J. Accuracy Assessment Algorithm Bat Bioacoustics Echolocation Survey Method Trade-off Amazonia Brasil Chiroptera Owing to major technological advances, bioacoustics has become a burgeoning field in ecological research worldwide. Autonomous passive acoustic recorders are becoming widely used to monitor aerial insectivorous bats, and automatic classifiers have emerged to aid researchers in the daunting task of analysing the resulting massive acoustic datasets. However, the scarcity of comprehensive reference call libraries still hampers their wider application in highly diverse tropical assemblages. Capitalizing on a unique acoustic dataset of >650,000 bat call sequences collected over a 3-year period in the Brazilian Amazon, the aims of this study were (a) to assess how pre-identified recordings of free-flying and hand-released bats could be used to train an automatic classification algorithm (random forest), and (b) to optimize acoustic analysis protocols by combining automatic classification with visual post-validation, whereby we evaluated the proportion of sound files to be post-validated for different thresholds of classification accuracy. Classifiers were trained at species or sonotype (group of species with similar calls) level. Random forest models confirmed the reliability of using calls of both free-flying and hand-released bats to train custom-built automatic classifiers. To achieve a general classification accuracy of ~85%, random forest had to be trained with at least 500 pulses per species/sonotype. For seven out of 20 sonotypes, the most abundant in our dataset, we obtained high classification accuracy (>90%). Adopting a desired accuracy probability threshold of 95% for the random forest classifier, we found that the percentage of sound files required for manual post-validation could be reduced by up to 75%, a significant saving in terms of workload. Combining automatic classification with manual ID through fully customizable classifiers implemented in open-source software as demonstrated here shows great potential to help overcome the acknowledged risks and biases associated with the sole reliance on automatic classification. © 2018 Elsevier B.V. 2020-06-15T21:36:24Z 2020-06-15T21:36:24Z 2019 Artigo https://repositorio.inpa.gov.br/handle/1/16800 10.1016/j.ecoinf.2018.11.004 en Volume 49, Pags. 45-53 Restrito Ecological Informatics
institution Instituto Nacional de Pesquisas da Amazônia - Repositório Institucional
collection INPA-RI
language English
topic Accuracy Assessment
Algorithm
Bat
Bioacoustics
Echolocation
Survey Method
Trade-off
Amazonia
Brasil
Chiroptera
spellingShingle Accuracy Assessment
Algorithm
Bat
Bioacoustics
Echolocation
Survey Method
Trade-off
Amazonia
Brasil
Chiroptera
López-Baucells, Adrià
Stronger together: Combining automated classifiers with manual post-validation optimizes the workload vs reliability trade-off of species identification in bat acoustic surveys
topic_facet Accuracy Assessment
Algorithm
Bat
Bioacoustics
Echolocation
Survey Method
Trade-off
Amazonia
Brasil
Chiroptera
description Owing to major technological advances, bioacoustics has become a burgeoning field in ecological research worldwide. Autonomous passive acoustic recorders are becoming widely used to monitor aerial insectivorous bats, and automatic classifiers have emerged to aid researchers in the daunting task of analysing the resulting massive acoustic datasets. However, the scarcity of comprehensive reference call libraries still hampers their wider application in highly diverse tropical assemblages. Capitalizing on a unique acoustic dataset of >650,000 bat call sequences collected over a 3-year period in the Brazilian Amazon, the aims of this study were (a) to assess how pre-identified recordings of free-flying and hand-released bats could be used to train an automatic classification algorithm (random forest), and (b) to optimize acoustic analysis protocols by combining automatic classification with visual post-validation, whereby we evaluated the proportion of sound files to be post-validated for different thresholds of classification accuracy. Classifiers were trained at species or sonotype (group of species with similar calls) level. Random forest models confirmed the reliability of using calls of both free-flying and hand-released bats to train custom-built automatic classifiers. To achieve a general classification accuracy of ~85%, random forest had to be trained with at least 500 pulses per species/sonotype. For seven out of 20 sonotypes, the most abundant in our dataset, we obtained high classification accuracy (>90%). Adopting a desired accuracy probability threshold of 95% for the random forest classifier, we found that the percentage of sound files required for manual post-validation could be reduced by up to 75%, a significant saving in terms of workload. Combining automatic classification with manual ID through fully customizable classifiers implemented in open-source software as demonstrated here shows great potential to help overcome the acknowledged risks and biases associated with the sole reliance on automatic classification. © 2018 Elsevier B.V.
format Artigo
author López-Baucells, Adrià
author2 Torrent, Laura
Rocha, Ricardo
E.D. Bobrowiec, Paulo
Palmeirim, Jorge Manuel
Meyer, Christoph F.J.
author2Str Torrent, Laura
Rocha, Ricardo
E.D. Bobrowiec, Paulo
Palmeirim, Jorge Manuel
Meyer, Christoph F.J.
title Stronger together: Combining automated classifiers with manual post-validation optimizes the workload vs reliability trade-off of species identification in bat acoustic surveys
title_short Stronger together: Combining automated classifiers with manual post-validation optimizes the workload vs reliability trade-off of species identification in bat acoustic surveys
title_full Stronger together: Combining automated classifiers with manual post-validation optimizes the workload vs reliability trade-off of species identification in bat acoustic surveys
title_fullStr Stronger together: Combining automated classifiers with manual post-validation optimizes the workload vs reliability trade-off of species identification in bat acoustic surveys
title_full_unstemmed Stronger together: Combining automated classifiers with manual post-validation optimizes the workload vs reliability trade-off of species identification in bat acoustic surveys
title_sort stronger together: combining automated classifiers with manual post-validation optimizes the workload vs reliability trade-off of species identification in bat acoustic surveys
publisher Ecological Informatics
publishDate 2020
url https://repositorio.inpa.gov.br/handle/1/16800
_version_ 1787141481123807232
score 11.755432

Registros relacionados