Using Post-Classification Enhancement in Improving the Classification of Land Use/Cover of Arid Region (A Case Study in Pishkouh Watershed, Center of Iran)
Authors
Abstract
Classifying remote sensing imageries to obtain reliable and accurate Land
Use/Cover (LUC) information still remains a challenge that depends on many factors such
as complexity of landscape especially in arid region. The aim of this paper is to extract
reliable LUC information from Land sat imageries of the Pishkouh watershed of central
arid region, Iran. The classical Maximum Likelihood Classifier (MLC) was first applied to
classify Land sat image of 15 July 2007. The major LUC identified were shrubland
(rangeland), agricultural land, orchard, river, settlement. Applying Post-Classification
Correction (PCC) using ancillary data and knowledge-based logic rules the overall
classification accuracy was improved from about 72% to 91% for LUC map. The improved
overall Kappa statistics due to PCC were 0.88. The PCC maps, assessed by accuracy
matrix, were found to have much higher accuracy in comparison to their counterpart MLC
maps. The overall improvement in classification accuracy of the LUC maps is significant
in terms of their potential use for land change modeling of the region.
