Object-based classification of a SPOT-4 image for mapping wetlands in the context of greenhouse gases emissions: the case of the Eastmain region, Québec, Canada
Bibliographic record
Abstract
(Studies on greenhouse gases (GHG) emitted by hydroelectric reservoirs have shown until now that the fate of carbon, following impoundment, seems to reach the fate of carbon in natural aquatic ecosystems after a decade or so. To adequately assess this assumption and then obtain the net GHG emissions from the Eastmain-1 hydroelectric reservoir, the carbon stock and GHG emissions from peatlands and different succession stages of forested areas need to be characterized prior to the reservoir impoundment. It is therefore important to characterize the carbon flow process (surface fluxes and sequestrated carbon) from these terrestrial systems prior to impoundment. The Canadian Wildlife Service of Environment Canada, Québec region, has developed an approach for mapping wetlands using Landsat/RADARSAT-1 satellite images. The method is based on image segmentation using the Definiens Professional software. The top-down object-based classification is based on the Canadian Wetland Classification System and quickly and precisely identifies ecologically meaningful wetland polygons. The main objective of this study is to produce a wetland map of the Eastmain River watershed using a SPOT-4 image aimed at identifying five classes of wetlands (bog, fen, marsh, swamp, shallow water) for a geographical unit of at least 1 ha, and to add to the peatland classes a description of their components, such as pool complexes and vegetation structures, to assign measured carbon values to these different peatland classes and scale up the data to obtain a regional carbon budget. The second objective of the study consists in determining whether SPOT-4 images can be used to map wetlands, using the object-based method developed with Landsat/RADARSAT-1 images, and if a finer spatial resolution would improve the wetland mapping results by adding information on wetland components. The SPOT-4 classification using the object-based method allowed the five main wetland classes to be identified in addition to pool complexes in three density classes (isolated, low density, and high density) and “bogs”/“fens” vegetation structure (treed or open) in peatland classes. Validation was done at two levels: (i) between the five classes of wetlands, and (ii) between pool complexes and vegetation structures. The overall accuracy was 81% for the first level and 75% for the second.
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 | 0.002 | 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".