Woodland Cover Change Assessment Using Decision Trees, Support Vector Machines and Artificial Neural Networks Classification Algorithms

Land cover change assessment is one of the main applications of remote sensed data. Change in forest cover have widespread effects on the provision of ecosystem services, and provide important feedbacks to climate change and biodiversity. Moreover, it will be extremely critical if the accuracy of image interpretation can be improved for better understanding the change of forest. Parametric methods such as maximum likelihood classification assume normally distribute remote sensor data, however, texture and elevation information usually are not normally distributed. As a result, some nonparametric methods are applied in this research. They are computationally fast and make no statistical assumptions regarding the distribution of data. Support vector machine, Neural net, Decision tree these three methods have been used to extract forest cover change in the study area which highest forest cover in Guangdong Heyuan. In this study, we analysed the potential of DTs as one technique for data mining for the analysis of the 1991 and 2004 Landsat TM datasets, respectively. The results were compared with those obtained using SVMs, and ANN. Overall, acceptable accuracies of over 88% were obtained in all the cases. In general, the DTs performed better than both ANN and SVMs.