Multiscale mapping of plant functional groups and plant traits in the High Arctic using field spectroscopy, UAV imagery and Sentinel-2A data
Bibliographic record
Abstract
Abstract The Arctic is warming twice as fast as the rest of the planet, leading to rapid changes in species composition and plant functional trait variation. Landscape-level maps of vegetation composition and trait distributions are required to expand spatially-limited plot studies, overcome sampling biases associated with the most accessible research areas, and create baselines from which to monitor environmental change. Unmanned aerial vehicles (UAVs) have emerged as a low-cost method to generate high-resolution imagery and bridge the gap between fine-scale field studies and lower resolution satellite analyses. Here we used field spectroscopy data (400–2500 nm) and UAV multispectral imagery to test spectral methods of species identification and plant water and chemistry retrieval near Longyearbyen, Svalbard. Using the field spectroscopy data and Random Forest analysis, we were able to distinguish eight common High Arctic plant tundra species with 74% accuracy. Using partial least squares regression (PLSR), we were able to predict corresponding water, nitrogen, phosphorus and C:N values (r 2 = 0.61–0.88, RMSEmean = 12%–64%). We developed analogous models using UAV imagery (five bands: Blue, Green, Red, Red Edge and Near-Infrared) and scaled up the results across a 450 m long nutrient gradient located underneath a seabird colony. At the UAV level, we were able to map three plant functional groups (mosses, graminoids and dwarf shrubs) at 72% accuracy and generate maps of plant chemistry. Our maps show a clear marine-derived fertility gradient, mediated by geomorphology. We used the UAV results to explore two methods of upscaling plant water content to the wider landscape using Sentinel-2A imagery. Our results are pertinent for high resolution, low-cost mapping of the Arctic.
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 | 0.001 |
| 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".