Land cover classification using Landsat data (study area: Pekan district, Pahang state, Malaysia)

In order to investigate the terrain changed in areas of urban, vegetation, bare land, and water type mapping in Pekan, Pahang of Malaysia using Landsat data. The data of a district of educational and research on years 2000 and 2013, were analyzed. First, will evaluating the quality of the image of Landsat data. There were no obvious errors noticeable on the geometric and radiometric. In order to estimate the accuracy of the map derived from classification, a ground truth map was prepared using strip sampling on map. Image classification was performed using original and synthetic bands for following four land types: urban, water, bare land, vegetation, and cloud types. Classification was performed using maximum likelihood (ML). The highest accuracy was obtained by using ML classifier. According to the results of this study, the spectral data of Landsat data have a large potential for land type mapping in Pekan area mapping.