University of Tehran Press Desert 2008-0875 17 2 2012 12 01 Land Cover Classification Using IRS-1D Data and a Decision Tree Classifier 137 146 32030 10.22059/jdesert.2013.32030 EN H.R. Keshtkar MSc. Graduate, University of Tehran, Karaj, Iran H. Azarnivand Professor, Faculty of Natural Resources, University of Tehran, Karaj, Iran H. Arzani Professor, Faculty of Natural Resources, University of Tehran, Karaj, Iran S.K. Alavipanah Professor, Faculty of Geography, University of Tehran, Tehran, Iran F. Mellati Instructor, Faculty of Environment and Natural Resources, Ferdowsi University, Mashhad, Iran Journal Article 2008 06 16 Land cover is one of basic data layers in geographic information system for physical planning and environmental<br />monitoring. Digital image classification is generally performed to produce land cover maps from remote sensing data,<br />particularly for large areas. In the present study the multispectral image from IRS LISS-III image along with ancillary data<br />such as vegetation indices, principal component analysis and digital elevation layers, have been used to perform image<br />classification using maximum likelihood classifier and decision tree method. The selected study area that is located in<br />north-east Iran represents a wide range of physiographical and environmental phenomena. In this study, based on Land<br />Cover Classification System (LCCS), seven land cover classes were defined. Comparison of the results using statistical<br />techniques showed that while supervised classification (i.e. MLC) produces an overall accuracy of about 72%; the<br />decision tree method, which improves the classification accuracy, can increase the results by about 7 percent to 79%. The<br />results illustrated that ancillary data, especially vegetation indices and DEM, are able to improve significantly<br />classification accuracy in arid and semi arid regions, and also the mountainous or hilly areas. https://jdesert.ut.ac.ir/article_32030_dd346f126250a4a9c45737841769652b.pdf