Advantages and limitations of using small, low-cost ROVs for seabed monitoring
Bibliographic record
Abstract
Monitoring methods, such as seabed bottom-towed cameras, sediment grabs, and benthic sledges, have limitations in spatial coverage, cause seabed disturbance, are restricted to soft-bottom substrates, and offer low flexibility for marine seabed monitoring. In this study, we investigate the potential of a non-invasive and simple underwater remotely operated vehicle (ROV) to enhance marine seabed monitoring. A tethered ROV equipped with a GoPro camera was deployed in three areas of Skagerrak at depths from 15-34 m to assess accuracy in species identification and substrate classification identified from still frames. The quality of still frames varied between areas due to turbidity, motion blur, and marine snow, which reduced the number of high-quality frames by approximately 20%. Classification of substrates and taxa identification were possible in the remaining still frames. Two different substrates were detected: sand and stone reef. Stone reefs had a lower occurrence compared to sand. A total of 10 taxa were detected in the two substrate types. The highest abundance was observed in the stone reef substrate compared to the sand substrate. Identification at the species level was limited due to the quality of the still frames, which affected the detectability of morphological traits. This study demonstrates that a widely accessible ROV can be used for marine monitoring. The ROV can be used in different substrates, and still frames provide valuable information on species composition, which can enhance the replicability of monitoring programs.
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 | 0.002 | 0.003 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".