Object-based classification of very high resolution panchromatic images for evaluating recent change in the structure of patterned peatlands
Bibliographic record
Abstract
An airphoto survey carried out at the La Grande hydroelectrical complex (James Bay, Quebec) revealed numerous signs of degradation of patterned fens, with a decrease in terrestrial vegetation and increase in ponds, a process known as aqualysis. The principal goal of this study is to provide information on the present and past (the last 50 years) state of patterned peatlands, associated with the pattern of the aquatic and terrestrial compartments, and to evaluate their changing cover using remote sensing techniques. In this paper, we present a semi-automated, object-based method for QuickBird panchromatic image classification. The method emphasizes contextual information. We have also integrated texture images calculated in advance as supplementary data layers in the process of segmentation and classification. The validation of QuickBird image classification shows that the proposed method can delineate peatlands with 95% producer’s accuracy and 88% user’s accuracy. The overall classification accuracy in the peatlands is 81%. The same robust technique was applied to the aerial photographs taken in 1957. The classification of QuickBird images and aerial photographs was used to assess the structural development of patterned peatlands in the La Grande 3 sector over the last 50 years. The analysis shows an increase in aquatic areas for only two out of seven studied peatlands. To confirm our hypothesis of active aqualysis, additional image analysis is required from other areas of the La Grande hydroelectrical complex where the aqualysis process is more pronounced.
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 | 0.004 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".