Characterization and Automated Classification of Underwater Acoustic Environments in the Western Black Sea Using Machine Learning Techniques
Growing concern over anthropogenic underwater noise, highlighted by initiatives like the Marine Strategy Framework Directive (MSFD) and its Technical Group on Underwater Noise (TG Noise), emphasizes regions like the Western Black Sea, where increasing activities threaten marine habitats. This region...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/13/7/1352 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849733671516372992 |
|---|---|
| author | Maria Emanuela Mihailov |
| author_facet | Maria Emanuela Mihailov |
| author_sort | Maria Emanuela Mihailov |
| collection | DOAJ |
| description | Growing concern over anthropogenic underwater noise, highlighted by initiatives like the Marine Strategy Framework Directive (MSFD) and its Technical Group on Underwater Noise (TG Noise), emphasizes regions like the Western Black Sea, where increasing activities threaten marine habitats. This region is experiencing rapid growth in maritime traffic and resource exploitation, which is intensifying concerns over the noise impacts on its unique marine habitats. While machine learning offers promising solutions, a research gap persists in comprehensively evaluating diverse ML models within an integrated framework for complex underwater acoustic data, particularly concerning real-world data limitations like class imbalance. This paper addresses this by presenting a multi-faceted framework using passive acoustic monitoring (PAM) data from fixed locations (50–100 m depth). Acoustic data are processed using advanced signal processing (broadband Sound Pressure Level (SPL), Power Spectral Density (PSD)) for feature extraction (Mel-spectrograms for deep learning; PSD statistical moments for classical/unsupervised ML). The framework evaluates Convolutional Neural Networks (CNNs), Random Forest, and Support Vector Machines (SVMs) for noise event classification, alongside Gaussian Mixture Models (GMMs) for anomaly detection. Our results demonstrate that the CNN achieved the highest classification accuracy of 0.9359, significantly outperforming Random Forest (0.8494) and SVM (0.8397) on the test dataset. These findings emphasize the capability of deep learning in automatically extracting discriminative features, highlighting its potential for enhanced automated underwater acoustic monitoring. |
| format | Article |
| id | doaj-art-82cf762297d041eb838cd1ec8632c527 |
| institution | DOAJ |
| issn | 2077-1312 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj-art-82cf762297d041eb838cd1ec8632c5272025-08-20T03:07:58ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-07-01137135210.3390/jmse13071352Characterization and Automated Classification of Underwater Acoustic Environments in the Western Black Sea Using Machine Learning TechniquesMaria Emanuela Mihailov0Research-Development and Innovation Center, Maritime Hydrographic Directorate “Comandor Alexandru Catuneanu”, Fulgerului Street No. 1, 900218 Constanta, RomaniaGrowing concern over anthropogenic underwater noise, highlighted by initiatives like the Marine Strategy Framework Directive (MSFD) and its Technical Group on Underwater Noise (TG Noise), emphasizes regions like the Western Black Sea, where increasing activities threaten marine habitats. This region is experiencing rapid growth in maritime traffic and resource exploitation, which is intensifying concerns over the noise impacts on its unique marine habitats. While machine learning offers promising solutions, a research gap persists in comprehensively evaluating diverse ML models within an integrated framework for complex underwater acoustic data, particularly concerning real-world data limitations like class imbalance. This paper addresses this by presenting a multi-faceted framework using passive acoustic monitoring (PAM) data from fixed locations (50–100 m depth). Acoustic data are processed using advanced signal processing (broadband Sound Pressure Level (SPL), Power Spectral Density (PSD)) for feature extraction (Mel-spectrograms for deep learning; PSD statistical moments for classical/unsupervised ML). The framework evaluates Convolutional Neural Networks (CNNs), Random Forest, and Support Vector Machines (SVMs) for noise event classification, alongside Gaussian Mixture Models (GMMs) for anomaly detection. Our results demonstrate that the CNN achieved the highest classification accuracy of 0.9359, significantly outperforming Random Forest (0.8494) and SVM (0.8397) on the test dataset. These findings emphasize the capability of deep learning in automatically extracting discriminative features, highlighting its potential for enhanced automated underwater acoustic monitoring.https://www.mdpi.com/2077-1312/13/7/1352underwater noiseBlack Seamachine learning (ML)soundscape analysisnoise source classificationdeep learning |
| spellingShingle | Maria Emanuela Mihailov Characterization and Automated Classification of Underwater Acoustic Environments in the Western Black Sea Using Machine Learning Techniques Journal of Marine Science and Engineering underwater noise Black Sea machine learning (ML) soundscape analysis noise source classification deep learning |
| title | Characterization and Automated Classification of Underwater Acoustic Environments in the Western Black Sea Using Machine Learning Techniques |
| title_full | Characterization and Automated Classification of Underwater Acoustic Environments in the Western Black Sea Using Machine Learning Techniques |
| title_fullStr | Characterization and Automated Classification of Underwater Acoustic Environments in the Western Black Sea Using Machine Learning Techniques |
| title_full_unstemmed | Characterization and Automated Classification of Underwater Acoustic Environments in the Western Black Sea Using Machine Learning Techniques |
| title_short | Characterization and Automated Classification of Underwater Acoustic Environments in the Western Black Sea Using Machine Learning Techniques |
| title_sort | characterization and automated classification of underwater acoustic environments in the western black sea using machine learning techniques |
| topic | underwater noise Black Sea machine learning (ML) soundscape analysis noise source classification deep learning |
| url | https://www.mdpi.com/2077-1312/13/7/1352 |
| work_keys_str_mv | AT mariaemanuelamihailov characterizationandautomatedclassificationofunderwateracousticenvironmentsinthewesternblackseausingmachinelearningtechniques |