Characterizing Southern Resident killer whale calls using a particle filter for frequency contour extraction
Bibliographic record
Abstract
With only 74 Southern Resident killer whales (SRKWs) remaining in the waters of the eastern Pacific, understanding these marine mammals is vital to their conservation. Invasive techniques such as focal follows or tagging whales could introduce stress to SRKWs. Instead, passive acoustic monitoring that uses a network of hydrophones one preferred tracking method, particularly in their critical habitat that overlaps the shipping lanes in the Salish Sea. The acoustic data, if processed in real-time using modern deep learning methods, can be used to detect whales and alert ships of the potential for spatial overlap to reduce risks of collision. In this project, we consider the differences in SRKW whale call types from archived recordings of each of J, K, and L pods recorded on regional hydrophones. The whale calls are extracted as functional observations in the time and frequency space from underwater recordings using a particle filter. Functional data analysis (e.g., functional clustering) are performed to characterize the whale calls and represent the variations in call types. Such statistical insights between pod-level call types should be useful for improving machine learning whale detection algorithms, and for identifying SRKW movement in a high ship traffic region of their critical habitat.
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 | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".