Passive Acoustic Monitoring (PAM) provides reliable, long-term data to support effective management of marine ecosystems. Baseline data and continuous monitoring are crucial to identifying long-term trends and sudden shifts in soundscapes and species occurrence patterns. This work examines whale presence and sources of anthropogenic noise in the Gulf of Mexico (GoMex) and Bermuda before proposing a method to accelerate acoustic analysis. In the GoMex, we used hurricane periods as baseline soundscapes with minimal human activity to examine contributions of vessel noise and seismic exploration to ambient sound levels. In Bermuda, we examined how the low-frequency soundscape has changed since 1966 and provided contemporary daily occurrence data for baleen and beaked whales. To increase the pace of acoustic analysis, we also propose a method of synthetic data creation for automated whale detection using machine learning. By inserting a known call onto background noise from a new environment using latent diffusion, this method eliminates the need to search for whale calls in the target soundscape and improves model performance by incorporating the noise profile of the new site into training data. The method can shorten time between acoustic data collection and reports to ecosystem managers, facilitating efficient transfer of the latest data.
Parry et al. (Wed,) studied this question.