An open-source acoustic detector for beluga whales, with evaluations in the Western Canadian Arctic
Bibliographic record
Abstract
Belugas (Delphinapterus leucas) face threats from various sources, including noise from oil and gas exploration, vessel traffic, and other human activities. Here we present the development of a deep learning-based acoustic detector to automatically detect the species, and measure its performance when applied to study sites in the western Canadian Arctic. We used over 20,000 individually annotated beluga vocalizations to train deep learning models in the binary task of classifying 3-second audio clips into containing beluga vocalizations or not. Approximately 7,000 annotated vocalizations were reserved for testing, and models were evaluated on their ability to correctly label audio clips of two lengths: 3 s and 60 s. The average F1 score (across 10 models) on 3 s clips was 0.82 with a standard deviation of 0.027, with the best model achieving 0.86. When applied to 60 s clips, the best model achieved an F1 score of 0.96. We used the trained classifier to build a detector that processes longer recordings and will make it available as an open-source tool.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.004 |
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".