An open-source bio-logger for studying cetacean behavior and communication

Abstract

Over the past decade, bioacoustics associated with diverse marine life has become the focus of increasing research. While fixed acoustic devices play important roles in characterizing localized soundscapes, animal-worn devices that record audio alongside physiological metrics provide richer portals to understanding cetacean communication and characterizing sounds in their environment. To facilitate scaling the collection of such multimodal datasets for deep learning applications and to encourage rapid prototyping for new recording capabilities, we present an open-source non-invasive bio-logger that can be deployed on marine animals to record high-quality audio synchronized with an extensible suite of behavioral and environmental sensors. The current implementation is tailored to investigating sperm whale communication and biology. It features four suction cups, three high-bandwidth synchronized hydrophones for audio analysis including directionality, GPS logging and transmission, and sensors for pressure, motion, orientation, temperature, and light. Its hardware and software are both open-source, with designs, fabrication details, and code available online. Lab-based experiments characterize and validate performance including shear adhesion forces, withstanding pressures equivalent to 560 m depths, battery life up to 16.8 hours, audio sensitivity of -205 dB re FS/μPa with a 96 dB dynamic range, multi-threaded data acquisition, drone-based deployments, and GPS-based recoveries. Field experiments record sperm whale vocalizations and behaviors spanning 10 deployments, 44 hours of recording, 20 dives, and up to 967 m depths. Altogether, this platform aims to advance the understanding of marine animal biology and communication within the rapidly evolving and intersecting areas of robotics, bioacoustics, and machine learning.

Fig 1. The CETI Bio-Logger on a wild sperm whale (left) and an overview of its main features (right).

This bio-logger is used by Project CETI to study the communication of sperm whales in the Eastern Caribbean off the coast of the island of Dominica. It is intended to be deployed on sperm whales in a non-invasive way (with suction cups) and record high-quality audio.

Fig 2. A six-layer PCB hosts all sensing, data acquisition, and computational electronics.

A: Top view before populating the Raspberry Pi and the recovery daughterboard. B: Bottom view. C: Fully populated top view.

Fig 3. System block diagram of CETI Bio-Logger electronics.

Fig 4. The software is designed in a modular architecture.

Central management threads and a dedicated data partition ensure reliability. Individual data acquisition threads facilitate extensions to new sensors, accommodate varying sampling rates, and leverage multiple CPU cores.

Fig 5. A state machine dynamically adapts the bio-logger’s recording behavior throughout a deployment.

This includes initialization of systems such as real-time clocks, enabling or disabling wireless capabilities, launching or stopping data acquisition threads, releasing suction, and shutting down. Illustrations are based on graphics by Alex Boersma.

Fig 6. The bio-logger has been deployed using pole-based and drone-based methods.

A: During pole-based deployments, a 7 m (21 ft) pole is fixed to a four degree-of-freedom arm mechanism that is mounted on the bow of a rigid inflatable boat (RIB) boat. B: During drone-based deployments, a modified racing drone holds the bio-logger with a bistable clamping mechanism.

Fig 7. Suction cup performance was evaluated under shear conditions by compressing the cup to create adhesion, applying a shear force, and measuring the cup displacement.

A: Shear resistance is much lower if the cup is not fully adhered before shear loading (using 50 N of preload force). B: The shear forces required to generate 3 mm or 10 mm displacements were comparable when testing on a rigid or compliant surface. Boxplots display median, upper and lower quartiles, inter quartile range (IQR), and outliers. White dots indicate means.

Fig 8. The sensitivity of each hydrophone channel was evaluated at varying frequencies (at 140 dB received SPL).

Fig 9. Using on-whale bio-loggers to record acoustic, behavioral, and environmental data during whale interactions provides valuable data for studying their communication.

A: Two tagged whales socialize with each other. B: A single tagged whale socializes with other whales.

Fig 10. Sensor data is synchronously recorded from environmental and behavioral sensors throughout a deployment.

Fig 11. The bio-logger successfully recorded sperm whale vocalizations.

A: Multiple echolocation clicks are evident as vertical lines in the spectrogram and waveform. B: The spectrogram and waveform of a single selected click help illustrate the frequency content distribution and the expected multi-pulse structure.