Comparing PolSAR, SAR and Optical Imagery Integration for Forest Canopy Height Estimation in Interior British Columbia, Canada
Bibliographic record
Abstract
Forest canopy height is an important indicator for estimating forest carbon stock and biomass, which have implications for multiple environmental issues. In remote sensing, canopy height is most commonly measured using light detection and ranging (LiDAR), which comes with satisfactory accuracy but also high costs. This study looked at the potential of using synthetic aperture radar (SAR) and polarimetric synthetic aperture radar (PolSAR), together with optical imagery, to estimate canopy height in an interior coniferous forest in British Columbia, Canada. A machine learning approach was used to derive the canopy height values. SAR backscatter coefficients from Sentinel-1 and ALOS-2, as well as PolSAR parameters from Sentinel-1, were used as independent variables. Sentinel-2 optical indices and bands were fused as independent variables in some trials in an attempt to further enhance model performance. LiDAR-extracted canopy height values served as ground truth for both model training and validation. We compared between using SAR backscatter and PolSAR parameters, as well as between using SAR backscatter from Sentinel-1 and ALOS-2. Results show that PolSAR parameters outperforms SAR backscatter in predicting canopy height, while ALOS-2 achieved better accuracy in canopy height estimation than Sentinel-1. Optical indices and bands were capable of enhancing model accuracy in all scenarios. To conclude, Sentinel-1 PolSAR parameters were the best predictor variables due to PolSAR’s ability to capture different scattering mechanisms under different canopy heights. Future studies should examine the potential of polarimetric synthetic aperture radar interferometry (PolInSAR) and ALOS-2 PolSAR to yield more accurate canopy height estimation over interior coniferous forests.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".