Using the background of fish photographs to quantify habitat composition in marine ecosystems
Bibliographic record
Abstract
Citizen science initiatives that collect opportunistic photos, or recordings, of living organisms (e.g. iNaturalist) are increasingly recognized for their importance in monitoring biodiversity. These projects are focussed primarily on recording the occurrence of individual species in space and time. Each photo potentially also contains additional valuable information. Here, we explored the amount and potential value of background information captured in fish photographs as a method to characterise reef habitats. The habitat in the background of fish photographs shared on iNaturalist was analysed for 6 sites across Australia. To measure accuracy of the habitat data captured in the iNaturalist photos, the habitat composition of each site was compared to standardised photo-quadrats from the citizen science project Reef Life Survey (RLS). Across all sites, 70-85% of the fish photographs from iNaturalist contained discernible biotic habitat in the background. Habitat composition as measured from the background of opportunistic fish photographs was similar to those of standardised surveys from RLS. In the face of rapid environmental change, opportunistic photographs collected by recreational divers represent a complementary way to rapidly and cost-effectively collect habitat data at more reefs and more frequently than is generally feasible with standardised scientific surveys.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".