Abstract
Tracking species with expanding ranges is crucial to conservation efforts and some typically temperate marine species are spreading northward into the Arctic Ocean. Risso’s (Gg) and Pacific white-sided (Lo) dolphins have been documented spreading poleward. Further, they make very similar sounds, so it is difficult for both human analysts and classification algorithms to tell them apart. Using automatic detectors and classifiers on large acoustic datasets would improve the efficiency of monitoring these species. variational mode decomposition (VMD) provides both an easier visualization tool for human analysts and exhibited robustness to background noise while extracting features in pulsed signals with very similar spectral properties. The goal of this work was to develop a new visualization tool using VMD and a statistics-based classification algorithm to differentiate similar pulsed signals. The proposed VMD method achieved 81% accuracy, even when using audio files with low SNR that did not have concurrent visual survey data. While many dolphins whistle, pulsed signals are one of the more useful vocalizations to use in detection and classification because of their species-specific acoustic features. Automating the VMD method and expanding it to other dolphin species that have very similar pulsed signals would complement current detection and classification methods and lead to a more complete understanding of ecosystem dynamics under a changing climate.
Highlights
Marine mammals shifting their habitat ranges may be because of climate change and these shifts can be monitored acoustically by placing underwater recorders throughout the ocean to listen for and track their vocalizations[1–3]
An algorithm that can eliminate background noise, emphasize frequency content in short signals, and use limited acoustic features to differentiate between species while being computationally efficient would advance the processing of marine mammal signals needed to track habitat expansion of species as the climate changes
Our Bayesian variational mode decomposition (VMD) Method and VMD-gram meet these advantageous requirements. They were tested on a difficult dataset—one that was sparse, void of whistles, lacked contextual clues beyond 4.5 s, and had many low SNR files. These difficulties are the reality for much underwater acoustic data, but future work includes testing this new method on a set of more robust datasets to determine how well our results generalize
Summary
Marine mammals shifting their habitat ranges may be because of climate change and these shifts can be monitored acoustically by placing underwater recorders throughout the ocean to listen for and track their vocalizations[1–3]. The Risso’s dolphin (Grampus griseus, or “Gg”) and Pacific white-sided dolphin (Lagenorhynchus obliquidens, or “Lo”) pulsed signals are a good case study for tracking effects of climate change because they have recently been documented expanding northward into the Bering and Chukchi Seas[2]. Their pulsed signals were recorded in the Arctic Ocean starting in 2009 in areas where they were previously presumed to be extralimital when visually spotted[5]. Their work was successfully used to associate click types with behaviors in a subsequent s tudy[16] This instilled confidence that the distinctive peak and notch patterns of the two species are sufficiently stereotyped over time for use in the new method presented here.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
