Mapping Riparian Habitat Availability in Canada's Agricultural Landscapes using Earth Observation
Bibliographic record
Abstract
Riparian zones disproportionately increase biodiversity.Monitoring them should be prioritized for sustainability.Unfortunately, agricultural riparian zones are often highly modified, narrow, and heterogenous, making imagery classification and monitoring more challenging.The Canadian government operationally maps all agriculture -it would be ideal to include the adjacent riparian land.Several classification and masking methods were tested on riparian zones in three watersheds (Ontario and Prince Edward Island) using several thematic resolutions to determine an operational classification method.A pixel-based 60 m buffer method using 5 m imagery with reduced thematic resolution was successful for riparian classification and was used to demonstrate application of the Riparian Wildlife Habitat Availability on Farmland Indicator.Including riparian land in the annual crop inventory is not operationally feasible until the higher-resolution imagery becomes less expensive, as the riparian zone is often too narrow to spectrally separate riparian vegetation using lower resolution imagery. GlossaryAAFC -Agriculture and Agri-Food Canada -Canadian government agency associated with agriculture. ACI -Annual Crop Inventory -Every year AAFC creates a classified map from Earth observation data of all crops across Canada.Biodiversity -A measure of how many different species and the number of individuals present in an area. DRAPE -Digital Raster Acquisition Project for Eastern Ontario.EO -Earth Observation-Images or data of the Earth collected using sensors.Habitat Capacity -The amount of habitat available for species in a region.Indicator -A calculation, measurement, or product of simulation from a complex model, or simplified model from available important input variables that shows changes in the system. LiDAR -Light Detection and Ranging. MLC -Maximum Likelihood Classification -Supervised classification algorithm.MMU -Minimum Mapping Unit-Smallest group of pixels needed as input for classification. NIR -Near Infrared wavelength.Operational -Routine, feasible procedure.Riparian -Land adjacent to water features such as rivers, lakes, streams, and wetlands.Typically, there is a moisture gradient and unique vegetation associated with this region.Riparian Buffer -A strip of land adjacent to a water feature measured perpendicular to the shore or edge.Riparian Habitat -Any land adjacent to water or wetlands used by a species of interest.xvi RWHAFI -Riparian Wildlife Habitat Availability on Farmland Indicator -An AAFC metric of habitat based on riparian land cover adjacent to farmland and an expansion/subset of the WHAFI.Species Richness -The number of different species present in an area. WHAFI -Wildlife Habitat Availability on Farmland Indicator -An AAFC metric of habitat based on the annual crop inventory.
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 | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 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".