TY - JOUR ID - 54077 TI - Comparison of different algorithms for land use mapping in dry climate using satellite images: a case study of the Central regions of Iran JO - Desert JA - JDESERT LA - en SN - 2008-0875 AU - Yousefi, Saleh AU - Mirzaee, Somayeh AU - Tazeh, Mehdi AU - Pourghasemi, Hamidreza AU - Karimi, Haji AD - Department of Watershed Management, Faculty of Natural Resources, Tarbiat Modares University, Noor, Iran AD - Department of Watershed Management, Faculty of Natural Resources, Lorestan University, Khoramabad, Iran AD - Faculty of Natural Resources, Ardekan University, Ardekan, Iran AD - Faculty of Natural Resources, Ilam University, Ilam, Iran Y1 - 2015 PY - 2015 VL - 20 IS - 1 SP - 1 EP - 10 KW - Arid regions KW - land cover KW - remote sensing KW - SVM DO - 10.22059/jdesert.2015.54077 N2 - The objective of this research was to determine the best model and compare performances in terms of producing landuse maps from six supervised classification algorithms. As a result, different algorithms such as the minimum distance ofmean (MDM), Mahalanobis distance (MD), maximum likelihood (ML), artificial neural network (ANN), spectral anglemapper (SAM), and support vector machine (SVM) were considered in three areas of Iran's dry climate. The selectedstudy areas for dry climates were Shahreza, Taft and Zarand in Isfahan, Yazd, and Kerman Provinces, respectively. ThreeLandsat ETM+ images and topographical maps of 1:25,000-scale were used in the present study. In addition, trainingsamples for each land use were constructed using GPS and extensive field surveys. The training sites were divided intotwo categories; one category was used for image classification and the other for classification accuracy assessment.Results show that for the dry climate areas, Maximum Likelihood and Support Vector Machine algorithms with averagesof 0.9409 and 0.9315 Kappa coefficients are the best algorithms for land use mapping. The ANOVA test was performed onKappa coefficients, and the result shows that there are significant differences at the 1% level, between the differentalgorithms for the dry climate zones. These results can be used for land use planning, as well as environmental and naturalresources purposes in study areas. UR - https://jdesert.ut.ac.ir/article_54077.html L1 - https://jdesert.ut.ac.ir/article_54077_a03ba2904e5acfaea28503c6a535198d.pdf ER -