Estimating beluga whale abundance from space: using drones to ground‐validate VHR satellite imagery
Bibliographic record
Abstract
Abstract Routine monitoring of cetaceans is imperative for understanding their population trends and making informed management decisions. However, the inherent nature of cetaceans and the marine ecosystems they inhabit make annual population surveys logistically and economically challenging with current survey methods. One emerging solution is utilizing very high‐resolution (VHR) satellite imagery, which is a logistically efficient method for providing an instantaneous view of areas spanning hundreds of square kilometers. The objective of this study was to determine two factors required to reliably conduct beluga whale population abundance estimates with VHR satellite imagery: (1) depths that beluga whales are visible in VHR satellite images, which are used to define availability bias correction factors, and (2) a comparison of abundance estimates in VHR satellite imagery to current aerial methods. We submerged beluga whale models to different depths in two different water clarities and determined that beluga whales are distinguished only at the surface in turbid water (Secchi depth: 2.56 m) and at depths of 0–2 m in clear water (Secchi depth: 4.04 m). Based on the proportion of time beluga whales spend at these depths, an availability bias correction factor for Western Hudson Bay beluga whales was defined as 2.40 ± 0.16 for turbid water and 1.89 ± 0.05 for clear water. Synchronous ground‐validation surveys determined availability corrected beluga whale abundance estimates in 0.31 m VHR satellite imagery ( n = 173 beluga whales) and imagery that was HD sharpened using a proprietary algorithm to approximate 0.15 m resolution ( n = 170) to be comparable to drone imagery ( n = 164). VHR satellite imagery has the potential to increase the frequency of beluga whale population surveys, which has become increasingly important as beluga whales face rapid ecosystem changes and increased anthropogenic disturbances.
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 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".