Dynamic spatiotemporal acoustic occurrence of North Atlantic right whales in the offshore Rhode Island and Massachusetts Wind Energy Areas

Automated bioacoustic analysis aids understanding and protection of both marine and terrestrial animals and their habitats across extensive spatiotemporal scales, and typically involves analyzing vast collections of acoustic data. With the advent of deep learning models, classification of important signals from these datasets has markedly improved. These models power critical data analyses for research and decision-making in biodiversity monitoring, animal behaviour studies, and natural resource management. However, deep learning models are often data-hungry and require a significant amount of labeled training data to perform well. While sufficient training data is available for certain taxonomic groups (e.g., common bird species), many classes (such as rare and endangered species, many non-bird taxa, and call-type) lack enough data to train a robust model from scratch. This study investigates the utility of feature embeddings extracted from audio classification models to identify bioacoustic classes other than the ones these models were originally trained on. We evaluate models on diverse datasets, including different bird calls and dialect types, bat calls, marine mammals calls, and amphibians calls. The embeddings extracted from the models trained on bird vocalization data consistently allowed higher quality classification than the embeddings trained on general audio datasets. The results of this study indicate that high-quality feature embeddings from large-scale acoustic bird classifiers can be harnessed for few-shot transfer learning, enabling the learning of new classes from a limited quantity of training data. Our findings reveal the potential for efficient analyses of novel bioacoustic tasks, even in scenarios where available training data is limited to a few samples.

show abstract

Establishing baselines for predicting change in ambient sound metrics, marine mammal, and vessel occurrence within a US offshore wind energy area

Van Parijs,

DeAngelis,

Aldrich

et al. 2023

ICES Journal of Marine Science

View full text Add to dashboard Cite

Evaluating potential impacts on marine animals or increased sound levels resulting from offshore wind energy construction requires the establishment of baseline data records from which to draw inference. This study provides 2 years of baseline data on cetacean species’ presence, vessel activity, and ambient sound levels in the southern New England wind energy area. With eight species/families present in the area for at least 9 months of the year, this area represents an important habitat for cetaceans. Most species showed seasonality, with peak daily presence in winter (harbour porpoise, North Atlantic right, fin, and humpback whales), summer (sperm whales), spring (sei whales), or spring and fall/autumn (minke whales). Delphinids were continuously present and blue whales present only in January. The endangered North Atlantic right whales were present year round with high presence in October through April. Daily vessel presence showed an increase from summer through fall/autumn. On average, ambient sound levels were lowest in summer and increased late 2021 through 2022 with most temporal variability occurring across lower frequencies. The area showed a complex soundscape with several species sharing time–frequency space as well as overlap of vessel noise with the communication range of all baleen whale species.

show abstract

Dynamic spatiotemporal acoustic occurrence of North Atlantic right whales in the offshore Rhode Island and Massachusetts Wind Energy Areas

Cited by 5 publications

References 77 publications

Biodiversity

Biodiversity

Global birdsong embeddings enable superior transfer learning for bioacoustic classification

Establishing baselines for predicting change in ambient sound metrics, marine mammal, and vessel occurrence within a US offshore wind energy area

Contact Info

Product

Resources

About