Video classification of hypoxic habitats and benthic communities in two productive freshwater embayments
Bibliographic record
Abstract
• Traditional benthic grabs were combined with underwater video to detect hypoxic habitats. • Significant grouping in video data was supported by cluster analysis of environmental parameters. • There was a significant separation of benthic communities among the selected video groups. • Hypoxic habitats had reduced species diversity and a higher proportion of tubificids. • Video analysis can detect hypoxic habitats once a baseline is established. Ongoing anthropogenic eutrophication and warming temperatures are expected to increase the extent and severity of hypoxia globally. Monitoring hypoxia has traditionally relied on costly surveys or sensor networks. While benthic macroinvertebrates are valuable indicators of hypoxia, community analysis is limited by small spatial scales of traditional grab sampling and labor-intensive processing. To address this, we combined benthic grab samples with underwater video to detect hypoxic habitats in two productive embayments of the Laurentian Great Lakes: Saginaw Bay, Lake Huron with periodic short-term hypoxia, and Hamilton Harbour, Lake Ontario with prolonged hypoxia. Using supervised classification, we identified significant grouping of in situ video data with cluster analysis, and then aligned video groups with environmental and biological datasets. These video groups were supported by cluster analysis of measured environmental variables, with clusters differing in duration of low near-bottom dissolved oxygen concentration and by depth. Independent cluster analysis confirmed significant separation of benthic communities among the selected video groups, with hypoxic habitats showing reduced species diversity and a higher proportion of tubificids. The gradient of conditions sampled in our study revealed assemblages of benthic invertebrates sensitive to and tolerant of hypoxia. The agreement among video, biological, and environmental data confirmed that video analysis can provide a novel, quick and reliable method to detect benthic habitats affected by hypoxia and determine their spatial extent once a baseline is established.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| 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 teacher head, 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".