Medium resolution land cover mapping of Canada from SPOT 4/5 data
Bibliographic record
Abstract
Medium resolution land cover is one of the most widely used geospatial datasets for environmental assessment in Canada. Canada's current coverage is from circa-2000 Landsat and is therefore becoming out-of-date. With an update of the medium resolution orthoimage coverage of Canada from circa-2000 30 m Landsat to 2005 - 2010 20 m SPOT 4-5 imagery, an opportunity presented itself to update Canada's land cover with improved spatial resolution. Previous experience mapping the Northern Land Cover of Canada (NLCC) taught us to efficiently map at the national scale from Landsat, however the SPOT dataset required new approaches to deal with problems related to phenology and a smaller image footprint compared to Landsat. This paper presents solutions to the problems of radiometric normalization and classification extension with the objective of producing a consistent and accurate medium resolution national scale land cover. A 20 m SPOT land cover of Canada's forested regions at a 16-class thematic level is presented with full validation using nearly 1600 reference points across Canada. The overall accuracy of the product is 71% for strict assessment and 85% if relaxed to account for geolocation errors. An assessment of the product along the treeline ecotone suggests an improvement over existing land cover, while northward the product merges better with the existing circa-2000 Northern Land Cover of Canada from Landsat.
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 | 0.005 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 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".