Multi-temporal RADARSAT-2 polarimetric SAR data for urban land-cover classification using an object-based support vector machine and a rule-based approach
Bibliographic record
Abstract
We have investigated multi-temporal polarimetric synthetic aperture radar (SAR) data for urban land-cover classification using an object-based support vector machine (SVM) in combinations of rules. Six-date RADARSAT-2 high-resolution polarimetric SAR data in both ascending and descending passes were acquired in the rural–urban fringe of the Greater Toronto Area during the summer of 2008. The major land-use/land-cover classes include high-density residential areas, low-density residential areas, industrial and commercial areas, construction sites, parks, golf courses, forests, pasture, water, and two types of agricultural crops. Various polarimetric SAR parameters were evaluated for urban land-cover mapping and they include the parameters from Pauli, Freeman and Cloude–Pottier decompositions, the coherency matrix, intensities of each polarization, and their logarithm forms. The multi-temporal SAR polarimetric features were classified first using an SVM classifier. Then specific rules were developed to improve the SVM classification results by extracting major roads and streets using shape features and contextual information. For the comparison of the polarimetric SAR parameters, the best classification performance was achieved using the compressed logarithmic filtered Pauli parameters. For the evaluation of the multi-temporal SAR data set, the best classification result was achieved using all six-date data (kappa = 0.91), while very good classification results (kappa = 0.86) were achieved using only three-date polarimetric SAR data. The results indicate that the combination of both the ascending and the descending polarimetric SAR data with an appropriate temporal span is suitable for urban land-cover mapping.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".