RECOGNITION OF URBAN FUNCTIONAL REGIONS AT STREET SCALE BASED ON LJ1-01 NIGHT-TIME LIGHT REMOTE SENSING AND MOBILE BIG DATA
Night-time light (NTL) remote sensing data has been widely used in the analysis of human activities at night for a large extent, such as light pollution monitoring and recognition of urban functional regions. In most previous studies, the spatial resolutions of NTL remote sensing data are rather low (e.g., 500 m or coarser). Besides, remote sensing classification of land use rather than land cover types is often a hard task. Due to the reasons, it is difficult to meet the demand of urban refined management. In this study, mobile big data and Luojia1-01 (LJ1-01) NTL remote sensing satellite data with higher spatial resolution are adopted for extracting urban functional regions at the street-level scale. Taking Shenzhen city as a case, mobile big data (i.e., the volume of mobile devices) with the accuracy of approximate 150 m (i.e., 7-bit GeoHash encoding format) is integrated with NTL remote sensing data. After a hot spot analysis, the correlation between the two types of data are analysed. The typical supervised classification algorithms including KNN, SVM and random forest are used to distinguish urban functional regions, which are represented by five types, namely residential, business and commercial, industrial, transportation and other areas. The results show the effectiveness in extracting land use types in cities by combination of Luojia1-01 night-time light remote sensing and mobile big data. This study provides a basis for monitoring night light pollution of residential area, urban planning and the construction of smart cities.