Evaluation of C-band SAR data for wetlands mapping
Bibliographic record
Abstract
This publication reports results of an experiment carried out to examine the potential of polarimetric C-band Synthetic Aperture Radar (SAR) for mapping various wetland classes found in the Mer Bleue region (near Ottawa, Canada). The Mer Bleue region was surveyed by the C-band (5.3 GHz) polarimetric (HH, HV, VH, VV) SAR of the Canada Centre for Remote Sensing (CCRS) at three times within the vegetation season: 16 June (spring flush for vegetation), 6 July (mature growth stage for vegetation) and 3 October 1995 (senescence). Signatures of six different cover types (forested and nonforested peat bog, marsh, open water, clearing and forests) have been derived as a function of incidence angle. Separability between various classes was used to determine the relationships between season(s) and polarization(s) needed to differentiate various wetland classes. A supervised classification was used for wetlands mapping by means of multipolarization data. These investigations demonstrate some of the capabilities of SAR at C-band for mapping wetlands. The cross-polarization data provided the best separation between the observed classes. The October dataset was better suited for discriminating between the classes present than the other periods observed. The overall accuracies of the classification are 73% for June, 73% for July and 86% for October. Classification using a single polarization has been investigated and the results have shown that the HH and cross-polarizations are better than VV polarization. For October, the percentage of all pixels correctly classified is 74% for HH polarization, 76% for cross-polarization, and 59% for VV polarization. Investigations were carried out to determine whether temporal changes can be used to increase the information content of single polarization C-band SAR data, which are now available from ERS-2 and RADARSAT satellites. They demonstrated that the use of multitemporal data acquired in June, July and October do not provide a substantial amelioration of the classification of wetlands when the differentiation is not possible in any single period.
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 | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 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 | 0.000 |
| 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".