An open-source bio-logger for studying cetacean behavior and communication
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.013 | 0.007 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".