Synergistic using medium-resolution and high-resolution remote sensing imagery to extract impervious surface for Dianci Basin

35th International Symposium on Remote Sensing of Environment

地球科学;生态环境科学

Hong, Liang^1,2 ; Yang, Kun^2 ; Deng, Ming^1 ; Liu, Cun^2

School of Geosciences and Info-Physics, Central South University, Changsha, 410083, China^1

College of Tourism and Geography Science, Yunnan Normal University, Kunming, 650500, China^2

关键词: Classification and regression tree;    High resolution remote sensing imagery;    Impervious surface area;    Lake basins;    Non-point source pollution;    Percent impervious surfaces;    Regression tree models;    Thematic mapper images;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/17/1/012159/pdf
DOI  :  10.1088/1755-1315/17/1/012159

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

The knowledge of impervious surfaces, especially the magnitude, location, geometry, spatial pattern of impervious surfaces, is significant to urban ecosystem studies, including urban hydrology, urban climate, land use planning and resource management.Impervious surface area (ISA) is considered a key indicator of environmental quality and can be used to address complex urban environmental issues, particularly those related to the health of urban watersheds. ISA is also an indicator of non-point source pollution or polluted runoff. Remote sensing offers a consistent framework for representing spatial patterns and rates of urbanization over time through accurate observations of impervious surface area. Most of the existing methods of extracting impervious surface based on remote sensing concentrate on an urban scale, but the rapid and accurate methods of extracting impervious surfaces in a basin scale are nearly nonexistent in China and abroad. In recent years,with the rapid urbanization especially surrounding the Dianchi water body, the impervious surface coverage rate also grows rapidly and results in severe degradation of basin water environment within Dianchi watershed. In this study, we developed an approach to extract impervious surface for Dianci Basin by synergistic using medium-resolution and high-resolution remote sensing imagery. Subpixel percent impervious surfaces at Thematic Mapper (TM) images were mapped using the classification and regression tree(CART) algorithm. Sub-pixel impervious surfaces at 30m resolution were mapped in this study area through regression tree models. The estimated ISA results were evaluated through independent ISA reference data derived from high resolution QuickBird. The results prove the suitability of the approach for a widely automated and mapping of impervious surfaces in a basin scale.