Detecting illegal campfires by drone-mounted thermal sensors in protected tropical rainforests
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Thermal drones are increasingly used for conservation tasks such as biodiversity monitoring and wildfire management, but their utility in combating illegal activities in tropical rainforests remains underexplored. This study assesses the potential of thermal drones to detect campfires associated with illegal poaching and gold mining in Costa Rica’s Osa Peninsula. We simulated illegal campfires placed under the forest canopy, and conducted 29 experimental thermal drone flights across five survey rounds along a 1-km riverbank. Hypothesised factors influencing detection success, including fire stage, time of day, and canopy cover, were analysed. The drone detected 21 of 23 campfires (91 per cent), with 73 per cent detected on the first flight. Increased canopy cover and older fires reduced detection success, but time of day had no significant impact. Detecting humans was more challenging than campfire detection. The findings suggest thermal drones can aid enforcement in tropical rainforests but should be used in repeated surveys to improve detection rates, especially in locations with dense canopies. Thermal drones could enhance efforts to monitor illegal hunting, mining and trespassing in remote protected areas, helping conservation teams save time and resources in challenging environments.
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.
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 it