Assessing the ability to detect and identify forage fish schools and species from Remotely Piloted Aircraft Systems video surveys in Coastal BC
Bibliographic record
Abstract
Remotely piloted aircraft systems (RPAS) present a potentially efficient method for quantifying surface-schooling forage fish species in important nearshore habitats. In British Columbia, this method could help fill data gaps in the distribution and abundance of key forage fish species (e.g. Pacific herring, Northern anchovy, Pacific sand lance). However, the ability to detect subsurface targets in marine habitats in aerial imagery is subject to errors caused by poor environmental conditions (e.g. high turbidity, waves, sun glint) and influenced by target characteristics (e.g. depth in the water column, contrast with background, size). Here, we aimed to evaluate the effects of environmental and target variables on fish detection in RPAS imagery through a controlled experiment (Objective 1) and tested this method at natural conditions in nearshore sites around Vancouver Island, BC (Objective 2) to create a method that can be used to quantify forage fish with maximum accuracy for future conservation purposes. In objective 1, by collecting imagery of a model fish school placed at different depths under a wide range of environmental conditions, we determined that RPAS surveys should target clear skies, low to moderate sun altitudes, glassy seas, low winds, and low turbidity. Target colour and depth also impacted the ability to detect the forage fish-like lures. In objective 2, we detected 612 forage fish schools in 750 minutes of RPAS video imagery collected around coastal Vancouver Island. We were able to identify shiner surfperch with high confidence but were not able to differentiate sand lance and herring very often. Additionally, we found that among school fish characteristics and environmental conditions, school size and contrast, and wave height and sun altitude greatly impacted the detectability of forage fish schools in RPAS imagery. These results will help inform future RPAS forage fish surveys and minimize detectability errors.
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 | 0.002 | 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 | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 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".