Uncertainty Problems in Image Change Detection
Bibliographic record
Abstract
Image Change Detection (ICD) methods are widely adopted to update large area land use/cover products. Uncertainty problems, however, are well known in such techniques, and a transparent assessment is necessary. In this study, a framework was proposed for evaluating binary land change utilizing remote sensing images. First, two widely adopted ICD methods were used to establish change maps. Second, binary decisions on Change (C) and Non-Change (NC) classes were reached through thresholding on change maps. Then, results were evaluated using two sampling designs: random sampling and stratified sampling. Analysis of results suggests that (1) for random sampling, with an increasing threshold on change variables, the overall accuracy increases and shows a large variance, which is highly correlated with the C omission error; and (2) comparatively, for stratified sampling, in which two strata (i.e., C and NC) were set, the overall accuracy shows a smaller variance and is highly associated with the NC commission error. The significant trends in accuracy assessments indicate the trade-offs between the C and NC classification errors in a binary decision and can present superficial or perfunctory accuracy evaluation in certain circumstances that the causes of error sources and uncertainty problems in ICD are not fully understood.
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 | 0.018 | 0.080 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 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".