Bridging the national data gap with Google earth engine and landsat imagery by developing annual land cover for Afghanistan
Bibliographic record
Abstract
The national-level land cover database is essential to sustainable landscape management, environmental protection, and food security. In Afghanistan, the existing national-level land cover data from 1972, 1993, and 2010 relied on satellite data from diverse sensors adopted three different land cover classification systems. This inconsistent land cover map across the various years leads to the challenge of assessing landscape changes that are crucial for management efforts. To address this challenge, a 19-year national-level land cover dataset from 2000 to 2018 was developed for the first time to aid policy development, settlement planning, and the monitoring of forests and agriculture across time. In the development of the 19 year span of land cover data products, a state-of-the-art remote sensing approach, employing a harmonized classification scheme was implemented through the utilization of Google Earth Engine (GEE). Publicly accessible Landsat imagery and additional geospatial covariates were integrated to produce an annual land cover database for Afghanistan. The generated dataset bridges historical data gaps and facilitates robust land cover change information. The annual land cover database is now accessible through https://rds.icimod.org/. This repository ensures that the annual land cover data is readily available to all users interested in comprehending the dynamic land cover changes happening in Afghanistan.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.007 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
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".