Confounding effects of environment-dependent propagation on automated classification of cetaceans
Bibliographic record
Abstract
Significant effort has been made over the last few decades to develop automated passive acoustic monitoring (PAM) systems capable of classifying cetaceans at the species level. The utility of such systems depends on their ability to operate across a wide range of ocean acoustic environments; however, anecdotal evidence suggests that site-specific acoustic propagation characteristics impact the performance of PAM systems. This is because properties of the ocean acoustic environment can be markedly different between regions and seasons in which PAM is used to observe cetaceans. Variability in propagation characteristics leads to differences in how each cetacean vocalization is distorted as it propagates along the source-receiver path. Unless these differences are accounted for, the acoustic environment will bias estimates of a PAM system’s performance. The impact of environment-dependent propagation on an aural classifier was assessed using a pulse propagation model. Simulations were conducted that showed the sensitivity of classifier performance to sound speed profile type. Furthermore, it was found that classifier performance was range-dependent, largely due to changes in signal-to-noise ratio (SNR); however, in some environments only 60% of the performance reduction was attributed to decreasing SNR, indicating that signal distortion—resulting from environment-dependent propagation—had a large impact on performance.
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 | 0.004 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".