Slocum Gliders Provide Accurate Near Real-Time Estimates of Baleen Whale Presence From Human-Reviewed Passive Acoustic Detection Information
Bibliographic record
Abstract
Mitigating the effects of human activities on marine mammals often depends on monitoring animal occurrence over long time scales, large spatial scales, and in real time. Passive acoustics, particularly from autonomous vehicles, is a promising approach to meeting this need. We have previously developed the capability to record, detect, classify, and transmit to shore information about the tonal sounds of baleen whales in near real time from long-endurance ocean gliders. We have recently developed a protocol by which a human analyst reviews this information to determine the presence of marine mammals, and the results of this review are automatically posted to a publicly accessible website, sent directly to interested parties via email or text, and made available to stakeholders via a number of public and private digital applications. We evaluated the performance of this system during two 3.75-month Slocum glider deployments in the southwestern Gulf of Maine during the spring seasons of 2015 and 2016. Near real-time detections of humpback, fin, sei, and North Atlantic right whales were compared to detections of these species from simultaneously recorded audio. Data from another 2016 glider deployment in the same area were also used to compare results between three different analysts to determine repeatability of results both among and within analysts. False detection (occurrence) rates on daily time scales were 0% for all species. Daily missed detection rates ranged from 17 to 24%. Agreement between two trained novice analysts and an experienced analyst was greater than 95% for fin, sei, and right whales, while agreement was 83-89% for humpback whales owing to the more subjective process for detecting this species. Our results indicate that the presence of baleen whales can be accurately determined using information about tonal sounds transmitted in near real-time from Slocum gliders. The system is being used operationally to monitor baleen whales in U.S., Canadian, and Chilean waters, and has been particularly useful for monitoring the critically endangered North Atlantic right whale throughout the northwestern Atlantic Ocean.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".