New insights into distinguishing temperate deciduous swamps from upland forests and shrublands with SAR
Bibliographic record
Abstract
Although wetlands are widely recognized for thier important role in providing ecosystem services, their abundance, spatial extent, and condition remain poorly constrained and at-risk of decline. Accurate mapping and monitoring are therefore essential for their protection. However, distinguishing swamps from upland forests and shrublands is especially challenging because optical sensors cannot detect water and/or saturated soil under dense canopies. Synthetic Aperture Radar (SAR) offers distinct advantages in this regard: (1) under certain conditions, microwaves can penetrate vegetation and provide a strong backscattered signal from double bounce when surface water or very wet soil are present, and (2) microwaves can penetrate clouds, providing an opportunity to monitor changes in moisture or the extent of flooding through time. In spite of these advantages, users may still find it difficult to know which wavelengths, incidence angles, polarization states, and times of year can be used to detect swamps because of the complexity of choices, and some confusing and conflicting results presented in the literature. The goal of this research was therefore to better elucidate the impacts of sensor and environmental characteristics on the seasonal backscattering behaviour observed in and separability between swamps and dry, upland forests and shrublands , as well as determine the need for additional ancillary data like digital elevation models and derivatives to improve mapping accuracy. Using SAR data from three sensors with two different wavelengths, various polarization states, and a range of incidence angles we: (1) investigate the drivers of variations in seasonal trends and the frequency and timing of changes among different SAR time series, and assess their impact on separability, (2) quantify the importance of acquisition timing, type, number of derivatives on the accuracy of Random Forest models. Our results show that a common pre-conception that longer wavelengths are preferred for distinguishing flooded versus upland forests and shrublands has proven overly general, that data acquired before leaf flush in the spring provides superior results, and that DEM data only provides an advantage when using sub-optimal SAR data.
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 | 0.000 | 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 | 0.000 | 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 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".