Multi-Scale Spectral Separability of Submerged Aquatic Vegetation Species in a Freshwater Ecosystem
Bibliographic record
Abstract
Optical remote sensing has been suggested as a preferred method for monitoring submerged aquatic vegetation (SAV), a critical component of freshwater ecosystems that is facing increasing pressures due to climate change and human disturbance. However, due to the limited prior application of remote sensing to mapping freshwater vegetation, major foundational knowledge gaps remain, specifically in terms of the specificity of the targets and the scales at which they can be monitored. The spectral separability of SAV from the St. Lawrence River, Ontario, Canada, was therefore examined at the leaf level (i.e., spectroradiometer) as well as at coarser spectral resolutions simulating airborne and satellite sensors commonly used in the SAV mapping literature. On a Leave-one-out Nearest Neighbor criterion (LNN) scale of values from 0 (inseparable) to 1 (entirely separable), an LNN criterion value between 0.82 (separating amongst all species) and 1 (separating between vegetation and non-vegetation) was achieved for samples collected in the peak-growing season from the leaf level spectroradiometer data. In contrast, samples from the late-growing season and those resampled to coarser spectral resolutions were less separable (e.g., inter-specific LNN reduction of 0.25 in late-growing season samples as compared to the peak-growing season, and of 0.28 after resampling to the spectral response of Landsat TM5). The same SAV species were also mapped from actual airborne hyperspectral imagery using target detection analyses to illustrate how theoretical fine-scale separability translates to an in situ , moderate-spatial scale application. Novel radiometric correction, georeferencing, and water column compensation methods were applied to optimize the imagery analyzed. The SAV was generally well detected (overall recall of 88% and 94% detecting individual vegetation classes and vegetation/non-vegetation, respectively). In comparison, underwater photographs manually interpreted by a group of experts (i.e., a conventional SAV survey method) tended to be more effective than target detection at identifying individual classes, though responses varied substantially. These findings demonstrated that hyperspectral remote sensing is a viable alternative to conventional methods for identifying SAV at the leaf level and for monitoring at larger spatial scales of interest to ecosystem managers and aquatic researchers.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| 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".