An Integrated Decision Tree Approach (IDTA) to Mapping Landcover Using Satellite Remote Sensing in Support of Grizzly Bear Habitat Analysis in the Alberta Yellowhead Ecosystem
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
RÉSUMÉDes données multisources comprenant des images satellitales Landsat de 1999, des descripteurs topographiques dérivés de MNA et des informations issues d'inventaires sur la végétation et intégrées dans un SIG ont été utilisés pour générer une carte détaillée de la classification du couvert afin de quantifier et d'analyser la distribution spatiale et la configuration des habitats d'ours grizzly dans la zone d'étude de l'écosystème de Yellowhead en Alberta. La carte était nécessaire dans le cadre plus global de l'évaluation de l'écosystème pour déterminer si les mouvements des ours et les patrons d'utilisation des habitats étaient affectés par les conditions changeantes du paysage et les activités humaines. Une approche intégrée IDTA, basée sur l'utilisation d'un arbre de décision, a été développée en incorporant le groupage non dirigé (K-moyennage), des règles de décision dérivées de façon empirique et basées sur l'utilisation de MNA et d'un SIG (proximité, pentes, etc.) et une classification dirigée basée sur le maximum de vraisemblance des classes de forêt et de végétation déduites de l'échantillonnage sur le terrain. Cette approche reposait sur une découverte antérieure, réalisée à partir d'une image Landsat de 1998 de la région, démontrant que la performance des différents classificateurs pouvait varier en fonction des diverses classes. La carte produite au moyen de la méthode IDTA s'est avérée d'une précision d'environ 80% (kappa=0,783) utilisant 494 points échantillonnés identifiés sans ambiguïté sur les orthophotographies numériques disponibles.SUMMARYMulti-source data consisting of 1999 Landsat satellite imagery, topographic descriptors derived from DEMs, and GIS-based vegetation inventory information have been used to generate a detailed landcover classification map to quantify and analyze the spatial distribution and configuration of grizzly bear habitat within the Alberta Yellowhead Ecosystem study area. The map is needed as part of a larger ecosystem assessment to help determine if bear movement and habitat use patterns are affected by changing landscape conditions and human activities. An Integrated Decision Tree Approach (IDTA) was developed that incorporated unsupervised (K-means) clustering, empirically-derived DEM- and GIS-based decision rules (proximity, slopes, etc.), and maximum likelihood supervised classification of forest and vegetation classes based on field sampling. This approach was based on an earlier finding, using a 1998 Landsat image in this area, that different classifiers performed at different levels of success in various classes. The map produced with the IDTA method was determined to be approximately 80% accurate (kappa = 0.783) using 494 randomly sampled points unambiguously identified on available digital orthophotography. Additional informationNotes on contributorsS.E. Franklin• S.E. Franklin, M.J. Hansen and C.C. Popplewell are with the Department of Geography, University of Calgary, 2500 University Drive, Calgary, Alberta T2N 1N4.G.B. Stenhouse• G.B. Stenhouse is with Foothills Model Forest, Box 6330, Hinton, Alberta T7V 1X6.M.J. Hansen• S.E. Franklin, M.J. Hansen and C.C. Popplewell are with the Department of Geography, University of Calgary, 2500 University Drive, Calgary, Alberta T2N 1N4.C.C. Popplewell• S.E. Franklin, M.J. Hansen and C.C. Popplewell are with the Department of Geography, University of Calgary, 2500 University Drive, Calgary, Alberta T2N 1N4.J.A. Dechka• J.A. Dechka is with GeoAnalytic Inc., 300, 700 - 4th Avenue S.W., Calgary, Alberta T2P 3J4.D.R. Peddle• D.R. Peddle is with the Department of Geography, University of Lethbridge, 4401 University Drive W., Lethbridge, Alberta T1K 3M4.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.004 |
| 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 it