Rice identification at the early stage of the rice growth season with single fine quad Radarsat-2 data
Bibliographic record
Abstract
The objective of the study was to determine whether rice identification and acreage estimation accuracy at the early stage of the rice growth season using single fine quad Radarsat-2 images could meet the demand of rice monitoring. The Leizhou site (20°52’N, 110°05’E) is located in Guangdong Province in southern China and is dominated by rice paddies. There was a lack of optical data acquisitions during certain years. There are two rice growth seasons per year. Multitemporal Radarsat-2 products were acquired in the early rice growth season of 2014. First, multi-temporal backscattering coefficients and polarimetric parameters based on H/A/Alpha and Yamaguchi polarimetric decomposition theories were extracted and analyzed to distinguish between rice paddies and other typical land cover types, which could help select the optimal rice growth stage and image characteristics for early season classification. Second, an object-oriented technique was applied to time series backscattering coefficient images (HH, HV, VH, VV), H/A/Alpha images (Entropy, Anistropy and Alpha) and Yamaguchi images (volume, double-bounce, surface and helix). Based on the segmentation images, the supervised Bayes, KNN, SVM and Decision tree classifier were used to identify rice. The results indicated that in flat area, 1) Backscatter images and Yamaguchi images were better than H/A/Alpha images in the rice identification application, and 2) At the early rice growth season, the 0430-Yamaguchi image combined with the objectoriented decision tree algorithm were capable of delivering highly accurate maps of rice (0.9236), while the 0524- backscatter image combined with the object-oriented decision tree algorithm could acquire the highest classification accuracy (0.9278) at the end of the rice growth season. Jointing stage is considered to be appropriate for rice identification at the early season. The study demonstrated that it was possible to identify rice at the early season with single quad C-SAR imagery.
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 | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 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".