Ordinal-level classification of sub-pixel tropical forest cover.
1994
Foody, G. M.
Remotely sensed data have considerable potential for mapping and monitoring tropical forests. For the production of regional scale maps which may be up-dated periodically, relatively coarse spatial resolution remotely sensed data, such as those from the NOAA AVHRR, are an appropriate source of data for such mapping applications. These maps, however, typically depict land cover at the nominal level only and may be unsuitable for the estimation of forest extent and dynamics. Results are presented of an investigation into the estimation of sub-pixel forest cover and classification at the ordinal level for tropical forest reserves in Ghana. Based on an analysis of Landsat MSS data that had been degraded spatially to a 1.2-km resolution, a strong correlation, r=0.94, was observed between predicted and actual sub-pixel forest cover. These estimates of sub-pixel forest cover may be used to produce an ordinal-level classification of forest cover. Using a classification accuracy assessment procedure that accounts for the higher information content of ordinal level data over nominal level data, the degree of agreement between predicted and actual class for a four-class classification of tropical forest cover was estimated to be 75.2%.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par Forestry Research Institute of Ghana
Découvrez la collection de ce fournisseur de données dans AGRIS