High-frequency side-scan sonar fish reconnaissance by autonomous underwater vehicles
Bibliographic record
Abstract
A dichotomy between depth penetration and resolution as a function of sonar frequency, draw resolution, and beam spread challenges fish target classification from sonar. Moving high-frequency sources to depth using autonomous underwater vehicles (AUVs) mitigates this and also co-locates transducers with other AUV-mounted short-range sensors to allow a holistic approach to ecological surveys. This widely available tool with a pedigree for bottom mapping is not commonly applied to fish reconnaissance and requires the development of an interpretation of pelagic reflective features, revisitation of count methods, image-processing rather than wave-form recognition for automation, and an understanding of bias. In a series of AUV mission test cases, side-scan sonar (600 and 900 kHz) returns often resolved individual school members, spacing, size, behavior, and (infrequently) species from anatomical features and could be intuitively classified by ecologists — but also produced artifacts. Fish often followed the AUV and thus were videographed, but in doing so removed themselves from the sonar aperture. AUV-supported high-frequency side-scan holds particular promise for survey of scarce, large species or for synergistic investigation of predators and their prey because the spatial scale of observations may be similar to those of predators.
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 | 0.001 |
| 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 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".