Application of DEM [digital elevation model] data to landsat image classification: evaluation in a tropical wet-dry landscape of Thailand.

摘要

Integration of ancillary data in digital image classification has been shown to improve land-use/land-cover discrimination and classification accuracy. The use of ancillary data, such as elevation, in Landsat thematic mapper classification to produce a land-use/land-cover map of the Sakae Krang watershed of Thailand was evaluated. Altogether, 12 feature sets containing the TM original bands, ratios, normalized differential vegetation index, principal components, and a digital elevation model were tested using unsupervised ISODATA clustering. Incorporation of elevation data was improved land-cover discrimination with relatively higher classification accuracy (77.5%) compared to TM data alone (65.3%). Further improvement in the classification accuracy (84.3%) was obtained when using elevation data under a supervised technique. The study also indicated that the classification results can be further improved by incorporating other geomorphometric variables, such as slope and soil moisture regime.