Remote Sensing and Land Use Extraction for Kernel Functions Analysis by Support Vector Machines with ASTER Multispectral Imagery

Land use is being considered as an element in determining land change studies, environmental planning and natural resourceapplications. the earth’s surface study by remote sensing has many benefits such as, continuous acquisition of data, broad regionalcoverage, cost effective data, map accurate data, and large archives of historical data. to study land use / cover, remote sensing as anefficient technology is always desired by experts. in this case, classification could be considered as one of the most importantmethods of extracting information from digital satellite images. selecting the best classification method and applying the propervalues for parameters extremely influences the trust level of extracted land use maps. this research is an applied study whichattempts to introduce support vector machines (svm) classification method, a recent development from the machine learningcommunity. moreover, we prove its potential for structure–activity relationship analysis on aster multispectral data of the centralcounty in the kabodar-ahang region of hamedan, iran. accuracy of svms method is varied by the type of kernel function and itsparameters. the purpose of this research is to find the accuracy of land use extraction by svm method using a polynomial and radialbasis functions kernel with their estimated optimum parameters in addition to comparing the results with maximum likelihoodmethod. most of the scientists imply that maximum likelihood method is suitable for classification. therefore, we try to comparesvm with ml method and to deliberate the efficiency of this new method in classification progress on aster multispectral data. theaccuracy of svm method by polynomial and radial basis functions kernel with optimum parameters and ml classification methodsachieved 93.18%, 91.77% and 88.35 % respectively. by comparing the accuracy of these methods, svm method by polynomialkernel was evaluated as suitable. therefore, we can suggest using svm method especially with the use of a polynomial kernel todetermine land use. in general, the results of this research are very practical in natural resources conservation planning and studies.also, this study verifies the effectiveness and robustness of svms in the classification of remotely sensed images.