A Relative Evaluation of Random Forests for Land Cover Mapping in an Urban Area

Random forests as a novel ensemble learning algorithm have significant potential for land cover mapping in complex areas but have not been sufficiently tested by the remote sensing community relative to some more popular pattern classifiers. In this research, we implemented random forests as a pattern classifier for land cover mapping from a satellite image covering a complex urban area, and evaluated the performance relative to several popular classifiers including Gaussian maximum likelihood (GML), multi-layer-perceptron networks (MLP), and support vector machines (SVM). Each classifier was carefully configured with the parameter settings recommended by recent literature, and identical training data were used in each classification. The accuracy of each classified map was further evaluated using identical reference data. Random forests were slightly more accurate than SVM and MLP but significantly better than GML in the overall map accuracy. Random forests and support vector machines generated almost identical overall map accuracy, but the former produced a smaller standard deviation of categorical accuracies, suggesting its better overall capability in classifying both homogeneous and heterogeneous land cover classes. Random forests have shown its robustness due to the most accurate classification on the whole, relatively balanced performance across all land cover categories, and relatively easier to implement. These findings should help promote the use of random forests for land cover classification in complex areas.