Integrating multiple data to identify building functions in China’s urban villages

Abstract

China’s urban villages have distinct characteristics compared with the ones in western countries. Identifying urban villages provides a basis for policymakers to evaluate and improve the effectiveness of urban planning in China and other developing countries. However, perhaps due to limitations of data acquisition among others, few urban studies have successfully identified urban villages at the building level. To fill the research gap, this paper has fused multiple sources of data and utilized a three-stage model to identify urban villages in Haizhu District (Guangzhou, China). The first stage discriminates residential buildings, offices, shops, and restaurants based on various peak times of bike trajectories in different types of buildings. However, the first stage could not distinguish the regular residential buildings (in cities) and residential buildings within urban villages due to the similarity of human activities between them. It then utilized a second stage to identify residential buildings within urban villages based on the area, height, and density of buildings. In the third stage, we used correction rules to identify buildings with mixed-use and single-use buildings within urban villages. The results showed that urban villages were mainly concentrated in the western and central regions of the Haizhu District. Most of them were adjacent to shopping buildings or high-rise residential buildings. Building height and density played critical roles in the characterization of residential buildings in urban villages. Our accuracy rate was around 85% when verified against ground-truth data.