Crop monitoring and yield estimation using polarimetric SAR and optical satellite data in southwestern Ontario
Bibliographic record
Abstract
Optical satellite data have been proven as an efficient source to extract crop information and monitor crop growth conditions over large areas. In local- to subfield-scale crop monitoring studies, both high spatial resolution and high temporal resolution of the image data are important. However, the acquisition of optical data is limited by the constant contamination of clouds in cloudy areas. This thesis explores the potential of polarimetric Synthetic Aperture Radar (SAR) satellite data and the spatio-temporal data fusion approach in crop monitoring and yield estimation applications in southwestern Ontario.\nFirstly, the sensitivity of 16 parameters derived from C-band Radarsat-2 polarimetric SAR data to crop height and fractional vegetation cover (FVC) was investigated. The results show that the SAR backscatters are affected by many factors unrelated to the crop canopy such as the incidence angle and the soil background and the degree of sensitivity varies with the crop types, growing stages, and the polarimetric SAR parameters. Secondly, the Minimum Noise Fraction (MNF) transformation, for the first time, was applied to multitemporal Radarsat-2 polarimetric SAR data in cropland area mapping based on the random forest classifier. An overall classification accuracy of 95.89% was achieved using the MNF transformation of the multi-temporal coherency matrix acquired from July to November. Then, a spatio-temporal data fusion method was developed to generate Normalized Difference Vegetation Index (NDVI) time series with both high spatial and high temporal resolution in heterogeneous regions using Landsat and MODIS imagery. The proposed method outperforms two other widely used methods. Finally, an improved crop phenology detection method was proposed, and the phenology information was then forced into the Simple Algorithm for Yield Estimation (SAFY) model to estimate crop biomass and yield. Compared with the SAFY model without forcing the remotely sensed phenology and a simple light use efficiency (LUE) model, the SAFY incorporating the remotely sensed phenology can improve the accuracy of biomass estimation by about 4% in relative Root Mean Square Error (RRMSE). The studies in this thesis improve the ability to monitor crop growth status and production at subfield scale.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 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) | 0.001 | 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".