Authors: Bin Chen*, University of California Davis, Yimeng Song, The Chinese University of Hong Kong, Bo Huang, The Chinese University of Hong Kong, Bing Xu, Tsinghua University
Topics: Remote Sensing, Urban Geography, Human-Environment Geography
Keywords: Human settlements; location-based data; remote sensing; downscaling
Session Type: Paper
Start / End Time: 10:00 AM / 11:40 AM
Room: Napoleon B1, Sheraton 3rd Floor
Presentation File: No File Uploaded
Satellite-based human settlement extraction methods have limited practical applications, due to merely studying the difference between human settlements with other land cover/use types in physical properties (e.g., spectral signature and land surface temperature) instead of considering the basic socio-economic property (e.g., human activities). To deal with this challenge, we proposed a novel method to accurately extract human settlement by integrating mobile phone locating-request (MPL) data and remotely sensed data. In this study, human settlements for selected cities were mapped at medium resolution (30 m) by downscaling the MPL data using Landsat NDVI adjusted weights. Additionally, by extending the proposed downscaling method to the MPL and MODIS data, a national-scale human settlement map at coarse resolution (250 m) in China was created with overall accuracy 92.87%. Compared with the widely used nighttime-light-based methods, the proposed method could solve the long-existing problems including data saturation, over glow, and blooming effects, as well as characterize human settlements with fine spatial details. Our study provides an alternative approach to human settlement extraction by combining its physical and socio-economic properties, and it can be easily adjusted with multi-scale remotely sensed data and applied to human settlement extraction at both regional and global scales.