Warm beach, warmer turtles: Using drone-mounted thermal infrared sensors to monitor sea turtle nesting activity
Bibliographic record
Abstract
For decades sea turtle projects around the world have monitored nesting females using labor-intensive human patrolling techniques. Here we describe the first empirical testing of a drone-mounted thermal infrared sensor for nocturnal sea turtle monitoring; on the Osa peninsula in Costa Rica. Preliminary flights verified that the drone could detect similar sea turtle activities as identified by on-the-ground human patrollers – such as turtles, nests and tracks. Drone observers could even differentiate tracks of different sea turtle species, detect sea turtle hatchlings, other wildlife, and potential poachers. We carried out pilot flights to determine optimal parameters for detection by testing different thermal visualization modes, drone heights, and gimbal angles. Then, over seven nights, we set up a trial to compare the thermal drone and operators’ detections with those observed by traditional patrollers. Our trials showed that thermal drones can record more information than traditional sea turtle monitoring methods. The drone and observer detected 20% more sea turtles or tracks than traditional ground-based patrolling (flights and patrols carried out across the same nights at the same time and beach). In addition, the drone operator detected 39 other animals/predators and three potential poachers that patrollers failed to detect. Although the technology holds great promise in being able to enhance detection rates of nesting turtles and other beach activity, and in helping to keep observers safer, we detail challenges and limiting factors; in drone imagery, current cost barriers, and technological advances that need to be assessed and developed before standardized methodologies can be adopted. We suggest potential ways to overcome these challenges and recommend how further studies can help to optimize thermal drones to enhance sea turtle monitoring efforts worldwide.
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 | 0.000 | 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 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".