Using Very High Resolution Remotely Piloted Aircraft Imagery to Map Peatland Vegetation Composition and Configuration Patterns within an Elevation Gradient
Bibliographic record
Abstract
GIS has developed over the decades from theory to highly accurate scientific observation using \nsatellites that provide high resolution imagery. Over the last decade drones have been \nintroduced to the world of GIS and have been able to overcome some of the issues present in \nsatellite and aerial imagery such as lower resolution for smaller objects and temporal \nconstraints. My thesis aims to explore how accurately RPAS can identify vegetation \ncommunities classed by morphological structure when compared to ground based vegetation \nsurveys in peatlands in Alberta. The wetland sites are situated across subregions that are \ncurrently not mapped by the Alberta Merged Wetland Inventory. Our research aims to answer \nthe following questions: 1) assess at how differing image resolution (2 cm and 3 cm) influence \nthe ability to identify morphologically functional classes within the RPAS imagery. 2) test the \naccuracy at which different morphological functional trait classes of vegetation could be digitized \nfrom remotely sensed imagery, highlight which classes had the highest and lowest accuracy \nand try to explain why. 3) Investigate if RPAS can be used to map out vegetation \ncomposition and configuration to replace ground based surveys. 4) Determine across an \nelevation gradient within the subregion groups (subalpine, montane and upper foothills) if there \nare any significant landscape metrics patterns that change across these subregions using \nelevation as a controlling variable. Flights were conducted with RPAS to collect imagery with a \nresolution of 2 cm and 3 cm then classified into digitized classes that represent the \nmorphological structure of different vegetation across 18 peatland. 13 different features were \nclassified in the 18 peatlands. All 18 peatland boundaries were delineated using slope, which \nremoved classes such as roads, objects, culverts, and bridges. The delineated peatlands were \nthen run through a landscape metric package in R to determine spatial patterns of vegetation at \nboth landscape and class level. Landscape Metrics revealed composition and configuration \ncharacteristics that were significant when plotted against elevation for landscape level metrics. \nReplication of the results once accuracy has been increased using either higher resolution \nimagery or other sensors to determine validity of the results is needed.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".