Data_Sheet_1_A Convolutional Neural Network for Automated Detection of Humpback Whale Song in a Diverse, Long-Term Passive Acoustic Dataset.pdf
Passive acoustic monitoring is a well-established tool for researching the occurrence, movements, and ecology of a wide variety of marine mammal species. Advances in hardware and data collection have exponentially increased the volumes of passive acoustic data collected, such that discoveries are no...
Main Authors: | , , , , , , , |
---|---|
Format: | Dataset |
Language: | unknown |
Published: |
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3389/fmars.2021.607321.s001 |
id |
ftsmithonian:oai:figshare.com:article/14228660 |
---|---|
record_format |
openpolar |
spelling |
ftsmithonian:oai:figshare.com:article/14228660 2023-05-15T16:35:52+02:00 Data_Sheet_1_A Convolutional Neural Network for Automated Detection of Humpback Whale Song in a Diverse, Long-Term Passive Acoustic Dataset.pdf Ann N. Allen (6313358) Matt Harvey (672827) Lauren Harrell (10316123) Aren Jansen (10316126) Karlina P. Merkens (6404561) Carrie C. Wall (10316129) Julie Cattiau (10316132) Erin M. Oleson (8070218) 2021-03-17T05:08:44Z https://doi.org/10.3389/fmars.2021.607321.s001 unknown https://figshare.com/articles/dataset/Data_Sheet_1_A_Convolutional_Neural_Network_for_Automated_Detection_of_Humpback_Whale_Song_in_a_Diverse_Long-Term_Passive_Acoustic_Dataset_pdf/14228660 doi:10.3389/fmars.2021.607321.s001 CC BY 4.0 CC-BY Oceanography Marine Biology Marine Geoscience Biological Oceanography Chemical Oceanography Physical Oceanography Marine Engineering deep machine learning convolutional neural network humpback whale (Megaptera novaeangliae) seasonal occurrence Hawaii Mariana Islands Kingman Reef passive acoustic monitoring Dataset 2021 ftsmithonian https://doi.org/10.3389/fmars.2021.607321.s001 2021-03-23T16:31:02Z Passive acoustic monitoring is a well-established tool for researching the occurrence, movements, and ecology of a wide variety of marine mammal species. Advances in hardware and data collection have exponentially increased the volumes of passive acoustic data collected, such that discoveries are now limited by the time required to analyze rather than collect the data. In order to address this limitation, we trained a deep convolutional neural network (CNN) to identify humpback whale song in over 187,000 h of acoustic data collected at 13 different monitoring sites in the North Pacific over a 14-year period. The model successfully detected 75 s audio segments containing humpback song with an average precision of 0.97 and average area under the receiver operating characteristic curve (AUC-ROC) of 0.992. The model output was used to analyze spatial and temporal patterns of humpback song, corroborating known seasonal patterns in the Hawaiian and Mariana Islands, including occurrence at remote monitoring sites beyond well-studied aggregations, as well as novel discovery of humpback whale song at Kingman Reef, at 5 ∘ North latitude. This study demonstrates the ability of a CNN trained on a small dataset to generalize well to a highly variable signal type across a diverse range of recording and noise conditions. We demonstrate the utility of active learning approaches for creating high-quality models in specialized domains where annotations are rare. These results validate the feasibility of applying deep learning models to identify highly variable signals across broad spatial and temporal scales, enabling new discoveries through combining large datasets with cutting edge tools. Dataset Humpback Whale Megaptera novaeangliae Unknown Pacific |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
ftsmithonian |
language |
unknown |
topic |
Oceanography Marine Biology Marine Geoscience Biological Oceanography Chemical Oceanography Physical Oceanography Marine Engineering deep machine learning convolutional neural network humpback whale (Megaptera novaeangliae) seasonal occurrence Hawaii Mariana Islands Kingman Reef passive acoustic monitoring |
spellingShingle |
Oceanography Marine Biology Marine Geoscience Biological Oceanography Chemical Oceanography Physical Oceanography Marine Engineering deep machine learning convolutional neural network humpback whale (Megaptera novaeangliae) seasonal occurrence Hawaii Mariana Islands Kingman Reef passive acoustic monitoring Ann N. Allen (6313358) Matt Harvey (672827) Lauren Harrell (10316123) Aren Jansen (10316126) Karlina P. Merkens (6404561) Carrie C. Wall (10316129) Julie Cattiau (10316132) Erin M. Oleson (8070218) Data_Sheet_1_A Convolutional Neural Network for Automated Detection of Humpback Whale Song in a Diverse, Long-Term Passive Acoustic Dataset.pdf |
topic_facet |
Oceanography Marine Biology Marine Geoscience Biological Oceanography Chemical Oceanography Physical Oceanography Marine Engineering deep machine learning convolutional neural network humpback whale (Megaptera novaeangliae) seasonal occurrence Hawaii Mariana Islands Kingman Reef passive acoustic monitoring |
description |
Passive acoustic monitoring is a well-established tool for researching the occurrence, movements, and ecology of a wide variety of marine mammal species. Advances in hardware and data collection have exponentially increased the volumes of passive acoustic data collected, such that discoveries are now limited by the time required to analyze rather than collect the data. In order to address this limitation, we trained a deep convolutional neural network (CNN) to identify humpback whale song in over 187,000 h of acoustic data collected at 13 different monitoring sites in the North Pacific over a 14-year period. The model successfully detected 75 s audio segments containing humpback song with an average precision of 0.97 and average area under the receiver operating characteristic curve (AUC-ROC) of 0.992. The model output was used to analyze spatial and temporal patterns of humpback song, corroborating known seasonal patterns in the Hawaiian and Mariana Islands, including occurrence at remote monitoring sites beyond well-studied aggregations, as well as novel discovery of humpback whale song at Kingman Reef, at 5 ∘ North latitude. This study demonstrates the ability of a CNN trained on a small dataset to generalize well to a highly variable signal type across a diverse range of recording and noise conditions. We demonstrate the utility of active learning approaches for creating high-quality models in specialized domains where annotations are rare. These results validate the feasibility of applying deep learning models to identify highly variable signals across broad spatial and temporal scales, enabling new discoveries through combining large datasets with cutting edge tools. |
format |
Dataset |
author |
Ann N. Allen (6313358) Matt Harvey (672827) Lauren Harrell (10316123) Aren Jansen (10316126) Karlina P. Merkens (6404561) Carrie C. Wall (10316129) Julie Cattiau (10316132) Erin M. Oleson (8070218) |
author_facet |
Ann N. Allen (6313358) Matt Harvey (672827) Lauren Harrell (10316123) Aren Jansen (10316126) Karlina P. Merkens (6404561) Carrie C. Wall (10316129) Julie Cattiau (10316132) Erin M. Oleson (8070218) |
author_sort |
Ann N. Allen (6313358) |
title |
Data_Sheet_1_A Convolutional Neural Network for Automated Detection of Humpback Whale Song in a Diverse, Long-Term Passive Acoustic Dataset.pdf |
title_short |
Data_Sheet_1_A Convolutional Neural Network for Automated Detection of Humpback Whale Song in a Diverse, Long-Term Passive Acoustic Dataset.pdf |
title_full |
Data_Sheet_1_A Convolutional Neural Network for Automated Detection of Humpback Whale Song in a Diverse, Long-Term Passive Acoustic Dataset.pdf |
title_fullStr |
Data_Sheet_1_A Convolutional Neural Network for Automated Detection of Humpback Whale Song in a Diverse, Long-Term Passive Acoustic Dataset.pdf |
title_full_unstemmed |
Data_Sheet_1_A Convolutional Neural Network for Automated Detection of Humpback Whale Song in a Diverse, Long-Term Passive Acoustic Dataset.pdf |
title_sort |
data_sheet_1_a convolutional neural network for automated detection of humpback whale song in a diverse, long-term passive acoustic dataset.pdf |
publishDate |
2021 |
url |
https://doi.org/10.3389/fmars.2021.607321.s001 |
geographic |
Pacific |
geographic_facet |
Pacific |
genre |
Humpback Whale Megaptera novaeangliae |
genre_facet |
Humpback Whale Megaptera novaeangliae |
op_relation |
https://figshare.com/articles/dataset/Data_Sheet_1_A_Convolutional_Neural_Network_for_Automated_Detection_of_Humpback_Whale_Song_in_a_Diverse_Long-Term_Passive_Acoustic_Dataset_pdf/14228660 doi:10.3389/fmars.2021.607321.s001 |
op_rights |
CC BY 4.0 |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.3389/fmars.2021.607321.s001 |
_version_ |
1766026170906705920 |