On evaluating the efficacy of air-borne synthetic aperture radar for detecting polar bears: A pilot study
Bibliographic record
Abstract
Knowing the location of polar bears (Ursus maritimus) in their winter dens is crucial for minimizing disturbance during this critical period in their life cycle. Previous research has used Forward Looking Infrared (FLIR) technology to detect bear dens but has only achieved a detection accuracy of 45% for single flights. The thermal nature of FLIR means that some bears are never detected nor are detectable using FLIR. In this paper we explore the use of Synthetic Aperture Radar (SAR) as an alternative polar bear detection technology in a simple pilot study in Churchill, Manitoba, Canada, during October 2021. In this experimental study, we focused on the detection of polar bears on the surface in the SAR images. The result of this study can inform future efforts to proceed to den-detection experiments. In this study, we achieved a polar bear identification accuracy of 66%, albeit with a small sample size. Many of the challenges we encountered involved low signal-to-noise ratios and imprecise flight paths. Concurrent research from other parties shows that neural networks and other machine learning techniques can overcome these challenges to some degree, suggesting that SAR may be a promising candidate to become an effective tool for polar bear detection, particularly when coupled with other sensors such as FLIR.
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 | 0.001 | 0.002 |
| 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".