Acoustic features as a tool to visualize and explore marine soundscapes: Applications illustrated using marine mammal passive acoustic monitoring datasets
Abstract Passive Acoustic Monitoring (PAM) is emerging as a solution for monitoring species and environmental change over large spatial and temporal scales. However, drawing rigorous conclusions based on acoustic recordings is challenging, as there is no consensus over which approaches are best suit...
Published in: | Ecology and Evolution |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley
2024
|
Subjects: | |
Online Access: | https://doi.org/10.1002/ece3.10951 https://doaj.org/article/29a90369bab54581b5e108c45e22cfbb |
id |
ftdoajarticles:oai:doaj.org/article:29a90369bab54581b5e108c45e22cfbb |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:29a90369bab54581b5e108c45e22cfbb 2024-09-15T18:11:14+00:00 Acoustic features as a tool to visualize and explore marine soundscapes: Applications illustrated using marine mammal passive acoustic monitoring datasets Simone Cominelli Nicolo' Bellin Carissa D. Brown Valeria Rossi Jack Lawson 2024-02-01T00:00:00Z https://doi.org/10.1002/ece3.10951 https://doaj.org/article/29a90369bab54581b5e108c45e22cfbb EN eng Wiley https://doi.org/10.1002/ece3.10951 https://doaj.org/toc/2045-7758 2045-7758 doi:10.1002/ece3.10951 https://doaj.org/article/29a90369bab54581b5e108c45e22cfbb Ecology and Evolution, Vol 14, Iss 2, Pp n/a-n/a (2024) ecoacoustics machine learning marine mammals passive acoustic monitoring UMAP Ecology QH540-549.5 article 2024 ftdoajarticles https://doi.org/10.1002/ece3.10951 2024-08-05T17:49:56Z Abstract Passive Acoustic Monitoring (PAM) is emerging as a solution for monitoring species and environmental change over large spatial and temporal scales. However, drawing rigorous conclusions based on acoustic recordings is challenging, as there is no consensus over which approaches are best suited for characterizing marine acoustic environments. Here, we describe the application of multiple machine‐learning techniques to the analysis of two PAM datasets. We combine pre‐trained acoustic classification models (VGGish, NOAA and Google Humpback Whale Detector), dimensionality reduction (UMAP), and balanced random forest algorithms to demonstrate how machine‐learned acoustic features capture different aspects of the marine acoustic environment. The UMAP dimensions derived from VGGish acoustic features exhibited good performance in separating marine mammal vocalizations according to species and locations. RF models trained on the acoustic features performed well for labeled sounds in the 8 kHz range; however, low‐ and high‐frequency sounds could not be classified using this approach. The workflow presented here shows how acoustic feature extraction, visualization, and analysis allow establishing a link between ecologically relevant information and PAM recordings at multiple scales, ranging from large‐scale changes in the environment (i.e., changes in wind speed) to the identification of marine mammal species. Article in Journal/Newspaper Humpback Whale Directory of Open Access Journals: DOAJ Articles Ecology and Evolution 14 2 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
ecoacoustics machine learning marine mammals passive acoustic monitoring UMAP Ecology QH540-549.5 |
spellingShingle |
ecoacoustics machine learning marine mammals passive acoustic monitoring UMAP Ecology QH540-549.5 Simone Cominelli Nicolo' Bellin Carissa D. Brown Valeria Rossi Jack Lawson Acoustic features as a tool to visualize and explore marine soundscapes: Applications illustrated using marine mammal passive acoustic monitoring datasets |
topic_facet |
ecoacoustics machine learning marine mammals passive acoustic monitoring UMAP Ecology QH540-549.5 |
description |
Abstract Passive Acoustic Monitoring (PAM) is emerging as a solution for monitoring species and environmental change over large spatial and temporal scales. However, drawing rigorous conclusions based on acoustic recordings is challenging, as there is no consensus over which approaches are best suited for characterizing marine acoustic environments. Here, we describe the application of multiple machine‐learning techniques to the analysis of two PAM datasets. We combine pre‐trained acoustic classification models (VGGish, NOAA and Google Humpback Whale Detector), dimensionality reduction (UMAP), and balanced random forest algorithms to demonstrate how machine‐learned acoustic features capture different aspects of the marine acoustic environment. The UMAP dimensions derived from VGGish acoustic features exhibited good performance in separating marine mammal vocalizations according to species and locations. RF models trained on the acoustic features performed well for labeled sounds in the 8 kHz range; however, low‐ and high‐frequency sounds could not be classified using this approach. The workflow presented here shows how acoustic feature extraction, visualization, and analysis allow establishing a link between ecologically relevant information and PAM recordings at multiple scales, ranging from large‐scale changes in the environment (i.e., changes in wind speed) to the identification of marine mammal species. |
format |
Article in Journal/Newspaper |
author |
Simone Cominelli Nicolo' Bellin Carissa D. Brown Valeria Rossi Jack Lawson |
author_facet |
Simone Cominelli Nicolo' Bellin Carissa D. Brown Valeria Rossi Jack Lawson |
author_sort |
Simone Cominelli |
title |
Acoustic features as a tool to visualize and explore marine soundscapes: Applications illustrated using marine mammal passive acoustic monitoring datasets |
title_short |
Acoustic features as a tool to visualize and explore marine soundscapes: Applications illustrated using marine mammal passive acoustic monitoring datasets |
title_full |
Acoustic features as a tool to visualize and explore marine soundscapes: Applications illustrated using marine mammal passive acoustic monitoring datasets |
title_fullStr |
Acoustic features as a tool to visualize and explore marine soundscapes: Applications illustrated using marine mammal passive acoustic monitoring datasets |
title_full_unstemmed |
Acoustic features as a tool to visualize and explore marine soundscapes: Applications illustrated using marine mammal passive acoustic monitoring datasets |
title_sort |
acoustic features as a tool to visualize and explore marine soundscapes: applications illustrated using marine mammal passive acoustic monitoring datasets |
publisher |
Wiley |
publishDate |
2024 |
url |
https://doi.org/10.1002/ece3.10951 https://doaj.org/article/29a90369bab54581b5e108c45e22cfbb |
genre |
Humpback Whale |
genre_facet |
Humpback Whale |
op_source |
Ecology and Evolution, Vol 14, Iss 2, Pp n/a-n/a (2024) |
op_relation |
https://doi.org/10.1002/ece3.10951 https://doaj.org/toc/2045-7758 2045-7758 doi:10.1002/ece3.10951 https://doaj.org/article/29a90369bab54581b5e108c45e22cfbb |
op_doi |
https://doi.org/10.1002/ece3.10951 |
container_title |
Ecology and Evolution |
container_volume |
14 |
container_issue |
2 |
_version_ |
1810448821089468416 |