Vocalization data and scripts to model reindeer rut activity using on-animal acoustic recorders and machine learning
For decades, researchers have employed sound to study the biology of wildlife, with the aim to better understand their ecology and behaviour. By utilizing on-animal recorders to capture audio from freely moving animals, scientists can decipher the vocalizations and glean insights into their behaviou...
Main Authors: | , , , |
---|---|
Format: | Other/Unknown Material |
Language: | unknown |
Published: |
Zenodo
2024
|
Subjects: | |
Online Access: | https://doi.org/10.5281/zenodo.11095409 |
id |
ftzenodo:oai:zenodo.org:11095409 |
---|---|
record_format |
openpolar |
spelling |
ftzenodo:oai:zenodo.org:11095409 2024-09-15T18:15:44+00:00 Vocalization data and scripts to model reindeer rut activity using on-animal acoustic recorders and machine learning Weladji, Robert Boucher, Alexander Holand, Øystein Kumpula, Jouko 2024-05-06 https://doi.org/10.5281/zenodo.11095409 unknown Zenodo https://doi.org/10.5061/dryad.w6m905qx8 https://zenodo.org/communities/dryad https://doi.org/10.5281/zenodo.11095408 https://doi.org/10.5281/zenodo.11095409 oai:zenodo.org:11095409 info:eu-repo/semantics/openAccess MIT License https://opensource.org/licenses/MIT Machine learning On-Animal Acoustic Recorder Rangifer tarandus Rutting Behaviour Convolutional neural network Reindeer info:eu-repo/semantics/other 2024 ftzenodo https://doi.org/10.5281/zenodo.1109540910.5061/dryad.w6m905qx810.5281/zenodo.11095408 2024-07-26T20:22:59Z For decades, researchers have employed sound to study the biology of wildlife, with the aim to better understand their ecology and behaviour. By utilizing on-animal recorders to capture audio from freely moving animals, scientists can decipher the vocalizations and glean insights into their behaviour and ecosystem dynamics through advanced signal processing. However, the laborious task of sorting through extensive audio recordings has been a major bottleneck. To expedite this process, researchers have turned to machine learning techniques, specifically neural networks, to streamline the analysis of data. Nevertheless, much of the existing research has focused predominantly on stationary recording devices, overlooking the potential benefits of employing on-animal recorders in conjunction with machine learning. To showcase the synergy of on-animal recorders and machine learning, we conducted a study at the Kutuharju research station in Kaamanen, Finland, where the vocalizations of rutting reindeer were recorded during their mating season. By attaching recorders to seven male reindeer during the rutting periods of 2019 and 2020, we trained convolutional neural networks to distinguish reindeer grunts with a 95% accuracy rate. This high level of accuracy allowed us to examine the reindeers' grunting behaviour, revealing patterns indicating that older, heavier males vocalized more compared to their younger, lighter counterparts. The success of this study underscores the potential of on-animal acoustic recorders coupled with machine learning techniques as powerful tools for wildlife research, hinting at their broader applications with further advancement and optimization. Funding provided by: Natural Sciences and Engineering Research Council Crossref Funder Registry ID: https://ror.org/01h531d29 Award Number: 327505 Funding provided by: NordForsk Crossref Funder Registry ID: https://ror.org/05bqzfg94 Award Number: 76915 Bioacoustics data were collected during the rutting seasons of 2019 and 2020. In 2019, ... Other/Unknown Material Kaamanen Rangifer tarandus Zenodo |
institution |
Open Polar |
collection |
Zenodo |
op_collection_id |
ftzenodo |
language |
unknown |
topic |
Machine learning On-Animal Acoustic Recorder Rangifer tarandus Rutting Behaviour Convolutional neural network Reindeer |
spellingShingle |
Machine learning On-Animal Acoustic Recorder Rangifer tarandus Rutting Behaviour Convolutional neural network Reindeer Weladji, Robert Boucher, Alexander Holand, Øystein Kumpula, Jouko Vocalization data and scripts to model reindeer rut activity using on-animal acoustic recorders and machine learning |
topic_facet |
Machine learning On-Animal Acoustic Recorder Rangifer tarandus Rutting Behaviour Convolutional neural network Reindeer |
description |
For decades, researchers have employed sound to study the biology of wildlife, with the aim to better understand their ecology and behaviour. By utilizing on-animal recorders to capture audio from freely moving animals, scientists can decipher the vocalizations and glean insights into their behaviour and ecosystem dynamics through advanced signal processing. However, the laborious task of sorting through extensive audio recordings has been a major bottleneck. To expedite this process, researchers have turned to machine learning techniques, specifically neural networks, to streamline the analysis of data. Nevertheless, much of the existing research has focused predominantly on stationary recording devices, overlooking the potential benefits of employing on-animal recorders in conjunction with machine learning. To showcase the synergy of on-animal recorders and machine learning, we conducted a study at the Kutuharju research station in Kaamanen, Finland, where the vocalizations of rutting reindeer were recorded during their mating season. By attaching recorders to seven male reindeer during the rutting periods of 2019 and 2020, we trained convolutional neural networks to distinguish reindeer grunts with a 95% accuracy rate. This high level of accuracy allowed us to examine the reindeers' grunting behaviour, revealing patterns indicating that older, heavier males vocalized more compared to their younger, lighter counterparts. The success of this study underscores the potential of on-animal acoustic recorders coupled with machine learning techniques as powerful tools for wildlife research, hinting at their broader applications with further advancement and optimization. Funding provided by: Natural Sciences and Engineering Research Council Crossref Funder Registry ID: https://ror.org/01h531d29 Award Number: 327505 Funding provided by: NordForsk Crossref Funder Registry ID: https://ror.org/05bqzfg94 Award Number: 76915 Bioacoustics data were collected during the rutting seasons of 2019 and 2020. In 2019, ... |
format |
Other/Unknown Material |
author |
Weladji, Robert Boucher, Alexander Holand, Øystein Kumpula, Jouko |
author_facet |
Weladji, Robert Boucher, Alexander Holand, Øystein Kumpula, Jouko |
author_sort |
Weladji, Robert |
title |
Vocalization data and scripts to model reindeer rut activity using on-animal acoustic recorders and machine learning |
title_short |
Vocalization data and scripts to model reindeer rut activity using on-animal acoustic recorders and machine learning |
title_full |
Vocalization data and scripts to model reindeer rut activity using on-animal acoustic recorders and machine learning |
title_fullStr |
Vocalization data and scripts to model reindeer rut activity using on-animal acoustic recorders and machine learning |
title_full_unstemmed |
Vocalization data and scripts to model reindeer rut activity using on-animal acoustic recorders and machine learning |
title_sort |
vocalization data and scripts to model reindeer rut activity using on-animal acoustic recorders and machine learning |
publisher |
Zenodo |
publishDate |
2024 |
url |
https://doi.org/10.5281/zenodo.11095409 |
genre |
Kaamanen Rangifer tarandus |
genre_facet |
Kaamanen Rangifer tarandus |
op_relation |
https://doi.org/10.5061/dryad.w6m905qx8 https://zenodo.org/communities/dryad https://doi.org/10.5281/zenodo.11095408 https://doi.org/10.5281/zenodo.11095409 oai:zenodo.org:11095409 |
op_rights |
info:eu-repo/semantics/openAccess MIT License https://opensource.org/licenses/MIT |
op_doi |
https://doi.org/10.5281/zenodo.1109540910.5061/dryad.w6m905qx810.5281/zenodo.11095408 |
_version_ |
1810453681797070848 |