Integrating CART Algorithm and Multi-source Remote Sensing Data to Estimate Sub-pixel Impervious Surface Coverage:A Case Study from Beijing Municipality,China

作     者：HU Deyong CHEN Shanshan QIAO Kun CAO Shisong 

作者机构：College of Resource Environment and TourismCapital Normal University College of Resources Science and TechnologyBeijing Normal University 

出 版 物：《Chinese Geographical Science》 (中国地理科学（英文版）)

年 卷 期：2017年第27卷第4期

页      面：614-625页

核心收录：

学科分类：083002[工学-环境工程] 0830[工学-环境科学与工程（可授工学、理学、农学学位）] 081802[工学-地球探测与信息技术] 08[工学] 0818[工学-地质资源与地质工程] 081602[工学-摄影测量与遥感] 0816[工学-测绘科学与技术] 

基　　金：Under the auspices of National Natural Science Foundation of China(No.41671339) 

主　　题：impervious surface impervious surface percentage classification and regression tree(CART) sub pixel sub pixel impervious surface percentage(SPIS) time series 

摘      要：The sub-pixel impervious surface percentage(SPIS) is the fraction of impervious surface area in one pixel,and it is an important indicator of *** remote sensing data,the spatial distribution of SPIS values over large areas can be extracted,and these data are significant for studies of urban climate,environment and *** develop a stabilized,multi-temporal SPIS estimation method suitable for typical temperate semi-arid climate zones with distinct seasons,an optimal model for estimating SPIS values within Beijing Municipality was built that is based on the classification and regression tree(CART) ***,models with different input variables for SPIS estimation were built by integrating multi-source remote sensing data with other auxiliary *** optimal model was selected through the analysis and comparison of the assessed accuracy of these ***,multi-temporal SPIS mapping was carried out based on the optimal *** results are as follows:1) multi-seasonal images and nighttime light(NTL) data are the optimal input variables for SPIS estimation within Beijing Municipality,where the intra-annual variability in vegetation is *** different spectral characteristics in the cultivated land caused by the different farming characteristics and vegetation phenology can be detected by the multi-seasonal images *** data can effectively reduce the misestimation caused by the spectral similarity between bare land and impervious *** testing,the SPIS modeling correlation coefficient(r) is approximately 0.86,the average error(AE) is approximately 12.8%,and the relative error(RE) is approximately 0.39.2) The SPIS results have been divided into areas with high-density impervious cover(70%–100%),medium-density impervious cover(40%–70%),low-density impervious cover(10%–40%) and natural cover(0%–10%).The SPIS model performed better in estimating values for high-density urban areas than other categories.3) Mul