European Ocean Biodiversity Information System
[ report an error in this record ]basket (0): add | show Print this page
Categorizing shallow marine soundscapes using explained clusters
Parcerisas, C.; Roca, I.T.; Botteldooren, D.; Devos, P.; Debusschere, E. (2023). Categorizing shallow marine soundscapes using explained clusters. J. Mar. Sci. Eng. 11(3): 550. https://dx.doi.org/10.3390/jmse11030550
In: Journal of Marine Science and Engineering. MDPI: Basel. ISSN 2077-1312; e-ISSN 2077-1312
Related to:
Calonge, A.; Develter, R.; Muñiz, C.; Parcerisas, C.; Reubens, J.; Boone, W.; Deneudt, K.; Debusschere, E. (2026). Scalable low-cost seabed landers: The missing link for sustained, integrated, long-term observations in dynamic shallow seas. Remote Sensing in Ecology and Conservation Online first: 1-9. https://dx.doi.org/10.1002/rse2.70072, more
Peer reviewed article  
Available in  Authors 
    Vlaams Instituut voor de Zee: Open access 387372 [ download pdf ]
Keyword
    Marine/Coastal
Author keywords
    eco-acoustics; interpretable machine learning; marine soundscape; Random Forest; shallow water; SHAP; UMAP; XAI
Project Top | Authors 
  • PhD: Marine Soundscapes in Shallow Water: Automated Tools for Characterization and Analysis
Authors  Top 
  • Parcerisas, C.
  • Roca, I.T.
  • Botteldooren, D.
  • Devos, P.
  • Debusschere, E.
Abstract
    Natural marine soundscapes are being threatened by increasing anthropic noise, particularly in shallow coastal waters. To preserve and monitor these soundscapes, understanding them is essential. Here, we propose a new method for semi-supervised categorization of shallow marine soundscapes, with further interpretation of these categories according to concurrent environmental conditions. The proposed methodology uses a nonlinear mapping of short-term spectrograms to a two-dimensional space, followed by a density-based clustering algorithm to identify similar sound environments. A random forest classifier, based on additional environmental data, is used to predict their occurrence. Finally, explainable machine learning tools provide insight into the ecological explanation of the clusters. This methodology was tested in the Belgian part of the North Sea, and resulted in clearly identifiable categories of soundscapes that could be explained by spatial and temporal environmental parameters, such as distance to the shore, bathymetry, tide or season. Classifying soundscapes facilitates their identification, which can be useful for policy making or conservation programs. Soundscape categorization, as proposed in this work, could be used to monitor acoustic trends and patterns in space and time that might provide useful indicators of biodiversity and ecosystem functionality change.
All data in the Integrated Marine Information System (IMIS) is subject to the VLIZ privacy policy Top | Authors