Comparing Support Vector Machines and Maximum Likelihood Classifiers for Mapping of Urbanization

Remote sensing of environmental processes and properties using Landsat imagery has evolved since its inception in 1972. Monitoring of land cover and its changes over space and time using classification algorithms is one of the most important uses of remote sensing. However, the reliability of the land cover products from remotely sensed data is dependent upon the accuracy of different classification parameters. In this study, we have applied and tested two land cover classification algorithms: support vector machine (SVM) and maximum likelihood (ML) for land cover classification of the Kathmandu Valley, Nepal, between 1988 and 2016. The results show that SVM has better classification accuracies compared to ML.