Recent developments, observations and lessons learned in the use of real-time passive acoustic monitoring from ocean gliders in order to mitigate harm to North Atlantic Right Whales and Southern Resident Killer Whales
Bibliographic record
Abstract
JASCO’s novel passive acoustic monitoring (PAM) system, OceanObserver was deployed in Canada’s Gulf of Saint Lawrence (GoSL) in autumn 2018 aboard a Slocum G3 glider. The purpose of this mission was to assist in the search for endangered North Atlantic Right Whales and other threatened cetaceans, and to report detections in near-real-time so that appropriate mitigation actions could be taken. This proposed presentation will provide results and lessons learned based upon the rigorous analysis and comparison of the real-time, in situ detections with the automated and manual detections derived from post-trial analysis of the recorded raw acoustic data. This post analysis has permitted an assessment of the performance of the automated detectors deployed at sea and the effectiveness of the real-time communication management software in getting marine mammal detections to shore-based stakeholders in a timely manner. It also has permitted the evaluation of the effectiveness of shore-based acoustic analysts tasked with the validation of the automated detections sent to shore.Whether the mission objective of “no false positives” in order to ensure the correctness of mitigation decisions will be discussed. The method of assessing performance will be described and empirical results presented. The application of this technology to SRKW conservation will be discussed.
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 | 0.011 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".