Evaluation of a machine learning-based algorithmic pipeline for real-time onboard removal of glider self-noise from passive acoustic data

Gliders are autonomous underwater vehicles that move by changing their buoyancy and center of gravity, making them a relatively quiet and thus attractive platform for collecting passive acoustic data for many applications, including soundscape/fisheries management, real-time monitoring of endangered whales, and acoustic propagation modeling/validation. Hydrophones can be integrated into the glider for automated analysis and identification from a purpose-built library, but broadband self-noise from internally moving motors and components must be removed to enhance precise signal processes for targets of interest. Passive acoustic data from two 2024 right whale monitoring missions in shallow coastal waters of the Georgia/Florida calving grounds were used with glider engineering data to develop signal processors and train a machine learning algorithm to identify and remove glider self-noise. Algorithm performance is evaluated using 2025 monitoring missions to assess potential improvement over current onboard filtering methods. Given the extremely shallow depths of operation for monitoring in the calving areas (15–25 m water depth), careful elimination of self-noise while retaining useful data may improve real-time detection capability. Algorithm performance on deep-water (>1000 m) data from 2022–2023 New England Sea Mounts Acoustics (NESMA) field experiments will be used to explore the viability of onboard, real-time use over a broader range of applications.