PCA-based denoising and automatic recognition of marine biological sounds to estimate Bio-voice Count Index for marine monitoring

Passive acoustic monitoring faces methodological challenges when isolating biological signals from anthropogenically dominated marine soundscapes. To address this, we present two novel computational workflows: (1) a Principal Component Analysis (PCA)-driven noise reduction algorithm that selectively...

Full description

Saved in:
Bibliographic Details
Main Authors: Bingjia Huang, Yi Wu, Yihua Lyu, Xi Yan, Mengmeng Tong, Xiaoping Wang
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125002894
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849233603018358784
author Bingjia Huang
Yi Wu
Yihua Lyu
Xi Yan
Mengmeng Tong
Xiaoping Wang
author_facet Bingjia Huang
Yi Wu
Yihua Lyu
Xi Yan
Mengmeng Tong
Xiaoping Wang
author_sort Bingjia Huang
collection DOAJ
description Passive acoustic monitoring faces methodological challenges when isolating biological signals from anthropogenically dominated marine soundscapes. To address this, we present two novel computational workflows: (1) a Principal Component Analysis (PCA)-driven noise reduction algorithm that selectively suppresses anthropogenic noise (e.g., vessel sounds) overlapping with biological frequency bands; and (2) an automatic Bio-voice Count Index (BCI) that quantifies target biological sounds through energy thresholding and adjustable frequency-weighting curve. We validated these methods using both synthetic soundscapes and 700 min of field recordings from coral reef ecosystems in Sanya, China. The PCA algorithm improved mean signal-to-noise ratios of field recordings by 5.3 dB (from 7.6 dB to 12.9 dB), effectively enhancing biological sound detectability. The BCI demonstrated strong correlations with biological metrics. When combined with the Acoustic Complexity Index, it improved the accuracy of fish abundance estimation compared to single-index approaches. Critically, our method reduces the analysis time by >90 % compared to manual methods. These tools provide ecologists with a reproducible framework for quantifying biodiversity in noisy environments, directly applicable to coral reef health monitoring and anthropogenic impact assessments.
format Article
id doaj-art-689dfe7ac96a465a976304c83d1fd3e6
institution Kabale University
issn 1574-9541
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-689dfe7ac96a465a976304c83d1fd3e62025-08-20T05:05:32ZengElsevierEcological Informatics1574-95412025-12-019010328010.1016/j.ecoinf.2025.103280PCA-based denoising and automatic recognition of marine biological sounds to estimate Bio-voice Count Index for marine monitoringBingjia Huang0Yi Wu1Yihua Lyu2Xi Yan3Mengmeng Tong4Xiaoping Wang5Ocean College, Zhejiang University, Zhoushan 316021, China; Key Laboratory of Marine Environmental Survey Technology and Application, Ministry of Natural Resources, Guangzhou 510000, ChinaOcean College, Zhejiang University, Zhoushan 316021, China; The Fourth Institute of Oceanography, Ministry of Natural Resources, Beihai 536000, ChinaKey Laboratory of Marine Environmental Survey Technology and Application, Ministry of Natural Resources, Guangzhou 510000, China; Nansha Islands Coral Reef Ecosystem National Observation and Research Station, Guangzhou 510300, ChinaHangzhou UTSIS Technology Co., Ltd, Hangzhou 310000, ChinaOcean College, Zhejiang University, Zhoushan 316021, China; Key Laboratory of Marine Environmental Survey Technology and Application, Ministry of Natural Resources, Guangzhou 510000, China; The Fourth Institute of Oceanography, Ministry of Natural Resources, Beihai 536000, China; Hainan Institute, Zhejiang University, Sanya 572000, ChinaOcean College, Zhejiang University, Zhoushan 316021, China; Donghai Lab, Zhoushan, Zhejiang 316021, China; Hainan Institute, Zhejiang University, Sanya 572000, China; Corresponding author at: Ocean College, Zhejiang University, Zhoushan 316021, China.Passive acoustic monitoring faces methodological challenges when isolating biological signals from anthropogenically dominated marine soundscapes. To address this, we present two novel computational workflows: (1) a Principal Component Analysis (PCA)-driven noise reduction algorithm that selectively suppresses anthropogenic noise (e.g., vessel sounds) overlapping with biological frequency bands; and (2) an automatic Bio-voice Count Index (BCI) that quantifies target biological sounds through energy thresholding and adjustable frequency-weighting curve. We validated these methods using both synthetic soundscapes and 700 min of field recordings from coral reef ecosystems in Sanya, China. The PCA algorithm improved mean signal-to-noise ratios of field recordings by 5.3 dB (from 7.6 dB to 12.9 dB), effectively enhancing biological sound detectability. The BCI demonstrated strong correlations with biological metrics. When combined with the Acoustic Complexity Index, it improved the accuracy of fish abundance estimation compared to single-index approaches. Critically, our method reduces the analysis time by >90 % compared to manual methods. These tools provide ecologists with a reproducible framework for quantifying biodiversity in noisy environments, directly applicable to coral reef health monitoring and anthropogenic impact assessments.http://www.sciencedirect.com/science/article/pii/S1574954125002894Acoustic indexCoral reefEco acousticsPassive acoustic monitoringPrincipal component analysis
spellingShingle Bingjia Huang
Yi Wu
Yihua Lyu
Xi Yan
Mengmeng Tong
Xiaoping Wang
PCA-based denoising and automatic recognition of marine biological sounds to estimate Bio-voice Count Index for marine monitoring
Ecological Informatics
Acoustic index
Coral reef
Eco acoustics
Passive acoustic monitoring
Principal component analysis
title PCA-based denoising and automatic recognition of marine biological sounds to estimate Bio-voice Count Index for marine monitoring
title_full PCA-based denoising and automatic recognition of marine biological sounds to estimate Bio-voice Count Index for marine monitoring
title_fullStr PCA-based denoising and automatic recognition of marine biological sounds to estimate Bio-voice Count Index for marine monitoring
title_full_unstemmed PCA-based denoising and automatic recognition of marine biological sounds to estimate Bio-voice Count Index for marine monitoring
title_short PCA-based denoising and automatic recognition of marine biological sounds to estimate Bio-voice Count Index for marine monitoring
title_sort pca based denoising and automatic recognition of marine biological sounds to estimate bio voice count index for marine monitoring
topic Acoustic index
Coral reef
Eco acoustics
Passive acoustic monitoring
Principal component analysis
url http://www.sciencedirect.com/science/article/pii/S1574954125002894
work_keys_str_mv AT bingjiahuang pcabaseddenoisingandautomaticrecognitionofmarinebiologicalsoundstoestimatebiovoicecountindexformarinemonitoring
AT yiwu pcabaseddenoisingandautomaticrecognitionofmarinebiologicalsoundstoestimatebiovoicecountindexformarinemonitoring
AT yihualyu pcabaseddenoisingandautomaticrecognitionofmarinebiologicalsoundstoestimatebiovoicecountindexformarinemonitoring
AT xiyan pcabaseddenoisingandautomaticrecognitionofmarinebiologicalsoundstoestimatebiovoicecountindexformarinemonitoring
AT mengmengtong pcabaseddenoisingandautomaticrecognitionofmarinebiologicalsoundstoestimatebiovoicecountindexformarinemonitoring
AT xiaopingwang pcabaseddenoisingandautomaticrecognitionofmarinebiologicalsoundstoestimatebiovoicecountindexformarinemonitoring