North Atlantic Right Whales in Newfoundland and Labrador waters, based on calls and opportunistic sightings
Bibliographic record
Abstract
With the increase of North Atlantic Right Whale (NARW) detections in Canadian waters, and the mortalities some have suffered here, there has been increased effort to detect and monitor the location and abundance of these whales, and ascertain how their habitat use patterns have changed. Automated detection and classification (DCS) of the underwater vocalizations of NARW is an essential tool to process the large volume of acoustic recording data gathered by Fisheries and Oceans Canada (DFO) to monitor these calling whales. DFO in Newfoundland and Labrador Region (referred to as NL hereafter) implemented an updated version of Baumgartner’s Low Frequency Detection and Classification System (LFDCS) to perform automated DCS of baleen whale vocalizations using acoustic data collected since 2009 from 69 successful deployments and nearly 150,000 h of recording time. In this study we used LFDCS to detect NARW presence, a task that it generally performed well, but in some offshore areas it generated false NARW detections within the context of smeared seismic airgun sounds or pervasive calling Humpback Whales. Although confounded by effects of high ambient noise, the small number of moorings over the large study area, and occasional Humpback Whale calls, confirmed NARW upcalls were detected occasionally off the Labrador coast, the south and east coasts of Newfoundland, along the margin of the Laurentian Channel, and in offshore areas. Most NARW upcalls were detected in the summer (Jun-Aug) or fall (Sep-Nov). Analysis of a subset of audio from 20 moorings across the study area found no NARW calls missed by LFDCS. However, on rare occasions during data validation, other more irregular NARW calls were sometimes missed by both our NL23 LFDCS library and the older Gom9 library when the LFDCS settings were not generalized sufficiently. Using seismically-contaminated acoustic recordings from the Grand Banks, differences between the Gom9 and NL23 libraries in precision and F1 (the harmonic mean of precision and recall) were marginal in the limited testing we conducted after creating the NL23 library. Nonetheless, improvements incorporated into our NL23 detector library streamlined data analysis and confirmed the presence of NARW in Newfoundland and Labrador waters. In addition, DFO NL’s opportunistic sightings database contains 29 records (totalling 44 whales) of free-swimming NARW between 2002 and 2023, with sightings made in almost all years. Recent sightings, with several matched to the New England Aquarium NARW catalogue, included a few individuals feeding in relatively shallow water not far from shore in Newfoundland. The confirmed and possible acoustic detections of NARW around Newfoundland and Labrador since at least 2009, and the sightings of this species in the region (particularly in recent years), corroborates that NARW are an occasional component of the marine megafauna in these waters.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".