OOS2025-1241, updated on 26 Mar 2025
https://doi.org/10.5194/oos2025-1241
One Ocean Science Congress 2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
Tursionet: detecting bottlenose acoustic interactions in the Pelagos sanctuary with small-scale fisheries. Aspects of acoustic data-preprocessing and detection techniques.
Davide Michel Lelong1, Michele Manghi2, Claudio Fossati1,2,3, Gianni Pavan1, Agnese Marchini1, Guido Gnone4, Fulvio Garibaldi5, Eleonora Coppolella2, Camilla Testori6, Federica Giorda6, and Cristina Casalone6
Davide Michel Lelong et al.
  • 1University of Pavia, Pavia, Italy
  • 2NAUTA Scientific SRL
  • 3CIAN int. Center of AI for Natural Acoustics;
  • 4Fondazione Acquario di Genova ONLUS
  • 5University of Genoa (DISTAV)
  • 6Istituto Zooprofilattico Sperimentale del Piemonte Liguria e Valle d'Aosta

The Tursionet project, funded by the Pelagos Initiative hosted by the Prince Albert II of Monaco Foundation, aims to study the acoustics interactions of bottlenose dolphins with different types of fishing gear from small-scale fisheries in the coastal waters in the Pelagos Sanctuary, a Marine Protected Area for marine mammals located in the Northwestern Mediterranean between France, Italy, and Monaco [1].

Several hydrophones have been deployed along the Ligurian coast near different types of static fishing gear (e.g. gillnets and pots) to monitor the acoustic interactions of bottlenose dolphins interacting with the nets and evaluate their frequency and possible impact.

The acoustics data collected will also be used to create an automated system to detect and signal the acoustic activity of dolphins to speed up the analysis for future works. Among the vast vocal repertoire of bottlenose dolphins [2], echolocation trains and final buzzes have been the most recorded and are thus the perfect candidate to build an automatic system of detection and classification. As in most automated systems, the data stream must go through several processing steps before it is fed into the classification system. In the present study, we investigate different preprocessing and feature extraction methods and test their advantages, disadvantages, and feasibility according to the classification system used.

This study aims to be a benchmark for the future and a table of discussion between different groups to find an optimal framework for the processing of acoustic signals of cetaceans, a crucial step in the pipeline of automated systems of cetacean bioacoustics.

[1] Tursionet project: https://www.tursionet.eu/en/
[2] Jones, B., Zapetis, M., Samuelson, M. M., & Ridgway, S. (2019). Sounds produced by bottlenose dolphins (Tursiops): a review of the defining characteristics and acoustic criteria of the dolphin vocal repertoire. Bioacoustics, 29(4), 399–440.
https://doi.org/10.1080/09524622.2019.1613265

How to cite: Lelong, D. M., Manghi, M., Fossati, C., Pavan, G., Marchini, A., Gnone, G., Garibaldi, F., Coppolella, E., Testori, C., Giorda, F., and Casalone, C.: Tursionet: detecting bottlenose acoustic interactions in the Pelagos sanctuary with small-scale fisheries. Aspects of acoustic data-preprocessing and detection techniques., One Ocean Science Congress 2025, Nice, France, 3–6 Jun 2025, OOS2025-1241, https://doi.org/10.5194/oos2025-1241, 2025.