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

Franklin, Steven E.; Stenhouse, Gordon B.; Hansen, M.; Popplewell, Charlene; Dechka, J.A.; Peddle, Derek R.

doi:10.1080/07038992.2001.10854899

Cited by 64 publications

(51 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach to producing a land cover map of the Foothills Model Forest was based on a decision-tree classifier, a unique combination of unsupervised and supervised classification techniques that rely on spectral, digital elevation model, and polygonal GIS data to extract the maximum information content from the assembled mapping database (Franklin et al 2001b). For personal use only.…”

Section: Mapping Land Cover In the Foothills Model Forestmentioning

confidence: 99%

“…In the Fundy Model Forest, the objective was to report the area of change in forest structure in each year for which suitable Landsat image data were available over a 15-year time period (1984-1999) (Franklin et al 2001a). In the Foothills Model Forest, validated grizzly bear (Ursus arctos horribilis) habitat maps were required (Franklin et al 2001b). The objective was to generate a Landsat TM land cover map that could provide a suitable input layer for models of bear habitat use and population dynamics.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Change detection and landscape structure mapping using remote sensing

Franklin¹,

Lavigne²,

Wulder³

et al. 2002

The Forestry Chronicle

View full text Add to dashboard Cite

Satellite remote sensing has long held promise as a powerful method of detecting forest canopy changes and mapping landscape structure over vast, often multi-jurisdictional forest areas. Landsat Thematic Mapper (TM) spectral response, for example, can be related accurately to changes in physiology and cover at a range of small to intermediate mapping scales. These data have been available continuously for almost 20 years; many areas have earlier satellite image archives stretching back to the 1970s. When considering spatially-explicit changes to landscapes-caused by natural and human disturbances-over this time period, digital, synoptic, and repeatable satellite remotely-sensed data are emerging as the observational media of choice that forest managers must possess and use wisely. In this paper, successful use of satellite remote sensing in two of Canada's Model Forests is described. First, in the Fundy Model Forest in southeastern New Brunswick, a 15-year TM image sequence was used to detect area changes associated with different harvesting and silvicultural practices. Second, in the Foothills Model Forest in west-central Alberta, grizzly bear habitat maps have been created from multi-scene TM land cover mosaics. These map products constitute critical information on landscape change and configuration required to answer key management questions. The paper concludes with a prognosis for the future role of satellite remote sensing in sustainable forest management as data quality continues to improve (i.e., increasing spatial, spectral, temporal, and radiometric resolutions), and methods are brought into the purview of forest managers and practitioners.Key words: remote sensing, landscape change, forest fragmentation, human disturbance, management information needs, habitat La télédétection a longtemps promis de se transformer en un outil puissant de détection des modifications du couvert forestier et de cartographie des structures du paysage sur de vastes territoires forestiers relevant souvent de plusieurs juridictions. La réponse spectrale du Landsat Thematic Mapper (TM), par exemple, peut être rattachée avec précision aux changements dans la physiologie et le couvert selon des échelles de cartographie de petites à intermédiaires. Ces données sont disponibles de façon continue depuis près de 20 ans; des archives d'images satellites existent pour certaines superficies depuis le début des années '70. Lorsqu'on examine les modifications au paysage qui peuvent être perçues de l'espace, à la suite de perturbations humaines ou naturelles, au cours de cette péri-ode, les données de télédétection numériques, synoptiques et répétitives s'avèrent être le média d'observation de choix que les amé-nagistes forestiers doivent détenir et utiliser à bon escient. Cet article décrit l'utilisation réussie de la télédétection spatiale pour deux forêts modèles du Canada. Premièrement, dans la Forêt modèle de Fundy du sud-est du Nouveau-Brunswick, une séquence d'images du TM au cours de 15 ans a été utilisée pour détecter les modific...

show abstract

Section: Mapping Land Cover In the Foothills Model Forestmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Change detection and landscape structure mapping using remote sensing

Franklin¹,

Lavigne²,

Wulder³

et al. 2002

The Forestry Chronicle

View full text Add to dashboard Cite

show abstract

“…It will support the standardization because it makes possible cross-comparable data: at spatial and temporal levels. In regard to habitat identification through RS recent researches have suggested different relevant considerations and requirements: study areas specific approaches; ecological expert knowledge implemented as decision rules; the implementation/inclusion of key input variables selected following specific characteristics of individual habitats; the integration of ancillary data into the classification processes, related to shape, texture, context; the use of non-parametric algorithms implemented through binary classifications or decision trees that allow to include nominal, derived and ancillary geospatial data and also are advantageous with scarce training samples; (Bock et al 2005;Boyd et al 2006;Foody et al 2007;Franklin et al 2001;Kerr and Ostrovsky 2003;Martínez et al 2010;Mücher et al 2009). …”

Section: Discussionmentioning

confidence: 99%

“…Some of these studies have focused on the mapping of one specific thematic class (Boyd et al 2006;Foody et al 2007) hypothesizing that non-parametric algorithm would be more suitable to habitats of conservation interest because of the scarce spatial distribution usually associated to them (the size of the training sample will be smaller). Other studies have combined that kind of techniques (binary classifications by DT) in hybrid approaches (Franklin et al 2001). The hybrid approaches assumes that parametric algorithms like standard maximum likelihood (ML) are the best option with spectrally different habitats while applies non-parametric algorithms to other complex habitats, in a so-called Integrated Decision Tree Approach (IDTA).…”

Section: The Use Of Binary Classifications By Decision Trees (Dt) (Bomentioning

confidence: 99%

“…The hybrid approaches assumes that parametric algorithms like standard maximum likelihood (ML) are the best option with spectrally different habitats while applies non-parametric algorithms to other complex habitats, in a so-called Integrated Decision Tree Approach (IDTA). The IDTA (Franklin et al 2001) consist on a process with a simple set of classification decision steps, readily understood and repeatable. The approach allows mixing unsupervised, supervised and stratification decision rules such that requirements for training data were minimized.…”

Section: The Use Of Binary Classifications By Decision Trees (Dt) (Bomentioning

confidence: 99%

See 1 more Smart Citation