Identifying direct deforestation drivers in Cameroon using deep learning and optical satellite data
Bibliographic record
Abstract
Deforestation rates have been increasing in the Congo Basin in recent years, especially in Cameroon. To support actions to slow deforestation, Earth Observation (EO) has been used extensively to detect forest loss, but approaches to automatically identify specific drivers of deforestation in a level of detail that allows for intervention prioritisation have been rare. In this paper, we use deep learning to classify direct deforestation drivers in Cameroon and create a country-specific dataset for this task. We also compare the effectiveness of two types of freely available optical satellite imagery: Landsat-8 (pan-sharpened to a 15 m spatial resolution) and NCIFI PlanetScope (4.77 m spatial resolution). Our detailed classification strategy includes 15 direct deforestation drivers for forest loss events taking place between 2015 and 2020. We obtain an overall accuracy of 82% (F1-score: 0.82) with Landsat-8 data and an overall accuracy of 76% (F1-score: 0.76) for NICFI PlanetScope. Despite a coarser spatial resolution, Landsat-8 performs better than NICFI PlanetScope overall, including for small-scale drivers, although results vary by class. With Landsat-8, using only a single-image approach, we achieve an accuracy of at least 70% for all classes except for ‘Hunting’, ‘Oil palm plantation’, and ‘Fruit plantation’. These results show the potential of using this approach to monitor or analyse land-use changes leading to deforestation with more refined classes than before. In addition, our study demonstrates the potential of leveraging existing available datasets and straightforwardly adapting a generalised framework for other tropical locations with a relatively small amount of location-specific data.
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) | 0.001 | 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 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".