TEMPORAL AND SPATIAL ANALYSIS OF CLASSIFICATION TREE FOR IMPERVIOUS SURFACE MAPPING FROM SENTINEL-2 MSI DATA

For studies of urban development, it is an important method for obtaining the distribution of impervious surface (IS) areas and their dynamic change from remote sensing data. The dilemma of the same spectrum for different features and different spectrums for the same features, posed by the complexity of the IS objects, is the fundamental obstacle encountered in the extraction of urban IS areas. In this study, an automatic extraction method for urban IS areas is proposed and analyzed, based on classification and regression tree (CART) and ensemble learning strategies. The Sentinel-2 MSI data of 30 cities in China from 2018 to 2020 were selected for IS extraction experiments. We perform temporal and spatial modeling of the splitting threshold offset in the classification model to explore the effect of time and space on IS extraction. The obtained offset models show that the temporal variation is not significant, while the spatial offsets have more obvious linear relationships.