Tracking Deforestation, Drought, and Fire Occurrence in Kutai National Park, Indonesia
Bibliographic record
Abstract
The dry lowland and mangrove forests of Kutai National Park (KNP) in Indonesia provide invaluable ecosystem services to local human populations (>200,000 in number), serve as immense carbon sinks to recapture anthropogenic emissions, and safeguard habitats for thousands of wildlife species including the critically endangered Northeast Bornean orangutan (Pongo pygmaeus morio). With recent reports of ongoing illegal logging and large-scale wildfires within this National Park, we sought to leverage the extensive catalogue and processing power of Google Earth Engine to track the rates and influences of forest loss within KNP over various time periods since 1997. We present estimates of forest loss from the Hansen Global Forest Change v1.9 dataset (2000–2021) which detected a loss of 15% (272 km2) of forest cover within KNP since 2000, half of which (137 km2) coincided with the El Niño-induced wildfires of 2015–2016. Using the MCD64A1 C6.1 MODIS dataset, we found significant spatial overlap between burned area and forest loss detections during the 2015–2016 period but identified considerable omissions in the burned area dataset over smallholder farms within KNP. We discuss the implications of deforestation in areas of primary orangutan habitat and how patterns of forest loss have influenced drought and fire dynamics within KNP. Finally, we compare time-series estimates of precipitation, the ENSO index, burned area, and forest loss to demonstrate that fire risk within KNP depends largely—but not exclusively—on drought severity, and that rates of non-fire (gradual) and fire-related (extreme) forest loss threaten the remaining forests of this National Park.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".