The effects of haze on the accuracy of satellite land cover classification

Abstract

Remote sensing data have long been the primary source for land cover map derivation. Nevertheless, for countries within haze-affected regions such as Malaysia, the existence of haze in the atmosphere tends to degrade the data quality. Such scenario is due to attenuation of recorded reflectances in which consequently affects the land cover classification task prior to the map derivation. This study aims to determine the effects of haze on the accuracy of land cover classification. Landsat-5 TM (Thematic Mapper) satellite data over the district of Klang, located in the state of Selangor, Malaysia were used. To account for haze effects, the study made use the Landsat datasets that have been integrated with haze layers. Maximum Likelihood (ML) classification was performed on the hazy datasets using training pixels extracted from the respective datasets. The accuracy of the classification was computed using confusion matrices where individual class and overall accuracy were determined. The results show that individual class accuracy is influenced not only by haze concentration but also class spectral properties. Overall classification accuracy declines with faster rate as visibility gets poorer.