No More Hidden Secrets: Human Rights Violation and Remote Sensing
Bibliographic record
Abstract
Aim: This study used both high resolution and medium resolution satellite imagery to test three semi-automated remote sensing methods, in an attempt to identify useful tools to support eye-witness testimony and reports on human rights violations. As huts are routinely burned down during attacks on a village, particularly in Sudan, the number of huts and villages burned can be used to corroborate on-the-ground reports. Methods: Three remote sensing methods (Supervised Classification, Change Detection, and Feature Extraction) were performed on imagery from both before the attacks in February 2006 and after the attacks to examine any useful trends that could be used by researchers when manually examining the satellite data. Results: In general, Supervised Classification methods performed unsatisfactorily. Some classes, such as water and agriculture, had high accuracy rates; however pixels classified as villages performed poorly. The Change Detection method delivered inconclusive results. Feature Extraction, when combined with the kernel density “hot spot” method, appears to be a useful tool to identify villages. The after imagery had no surviving villages in the study area, so Feature Extraction could not be completed on the after imagery and an accurate assessment of the method cannot be fully ascertained. Conclusions: The results of this study indicate that Feature Extraction is a useful ancillary tool to the practice of manual identification, particularly in places similar to Darfur with semi-arid grassland and rural huts and villages. In addition, the kernel density function when paired with Feature Extracted is a useful tool for visual analysis of clustered villages.
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 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 | 0.001 | 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 | 0.003 | 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 teacher head, 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".