Comparison of different classification algorithms in satellite imagery to produce land use maps (Case study: Noor city)

Land use mapping is one of the key factors in studies of environment and natural resources management. Mapping land use is often one of the most expensive parts of natural resources and environmental projects. Satellite data is one of the fastest and most cost-effective methods for mapping land use that is available for researchers. In recent years, researchers from the different methods of land use maps have been produced using this data. There is the different method to classify the images. Each method has advantages and disadvantages. The aim of this research is to determine the best images nine supervised classification methods to extract land use map of the Noor city by ETM+ sensor. The results showed that the SVM classification by 0.9503 factor kappa coefficient and 90.94% overall accuracy is better than other methods. The accuracy of the order of priority 9 that is, SVM, Neural network, Mahalanobis distance, Maximum likelihood, Minimum distance from the mean, Spectral angle mapper, Spectral information divergence, parallel piped and binary code. All the research results of this study can be using the correct classification. Land use maps can be extracted with higher accuracy.