Multiyear Crop Monitoring Using Polarimetric RADARSAT-2 Data
Bibliographic record
Abstract
This paper studies the feasibility of monitoring crop growth based on a trend analysis of three elementary radar scattering mechanisms using three consecutive years (2008–2010) of RADARSAT-2 (R-2) Fine Quad Mode data. The polarimetric synthetic aperture radar analysis is based on the Pauli decomposition. Multitemporal analysis is applied to RGB images constructed using surface scattering, double-bounce, and volume scattering, along with intensity analysis of these scattering mechanisms. The test site is located in Eastern Ontario, Canada where the cropping system is dominated by corn, spring wheat, and soybeans. Each crop has unique physical structural characteristics which provide different responses for these scattering mechanisms. Significant changes occur in these scattering mechanisms as the crops move from one phenological stage to the next. By monitoring these changes over the season, the crop growth cycle from emergence to harvest can be observed. When harvest occurs, the backscatter intensities change significantly, and these changes aid in identifying crops. The temporal evaluation of the intensity of the scattering mechanisms generally track the measured leaf area index and observed phenological plant development. Changes in growth stage are crop type specific. Thus, to monitor changes in crop phenology and the occurrence of harvest activities, knowledge of the crop grown in any particular field is required. To accommodate this requirement, a maximum likelihood classification was performed on the R-2 data to produce a crop map. An overall classification accuracy of 85$\%$was achieved.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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 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".