A framework to detect and understand thematic places of a city using geospatial data. (February 2021)

• Record Type: Journal Article
• Authors: Hu, Sheng; Xu, Yongyang; Wu, Liang; Wu, Xincai; Wang, Run; Zhang, Ziwei; Lu, Rujuan; Mao, Wei
• Is Part Of: Cities. Volume 109(2021)
• Publication Date: 2021-02
• Subjects: Urban perception -- Thematic place -- Geospatial data -- Community detection; City planning -- Periodicals; Urban policy -- Periodicals; 711.4
• DOI: 10.1016/j.cities.2020.103012
• Languages: English
• ISSNs: 0264-2751

Abstract

Abstract: The best way of sensing places has long been an interest in GIScience and urban studies. Previous studies detect and understand places via traditional human participant-oriented studies, which are laborious, time-consuming, and sometimes subjective. The proliferation of multi-sourced geospatial data brings unprecedented opportunities for researchers to improve assessment and understanding of places in cities. However, it remains insufficient to explore place based on a single or naïve set of geospatial data owing to issues of completeness and bias. Of particular interest is extracting and understanding thematic place using geospatial data. In this paper, we attempt to extract thematic place at a community scale and investigate the potential capability of multi-sourced geospatial data to understand extracted place. First, thematic places were constructed by integrating urban road networks and community detection methods in a complete network field. Then, we implemented quantitative geographical semantic analyses using geo-tagged street view images and point-of-interest data to investigate thematic places at a community scale for urban perception. A case study in a high-density urban environment, Wuhan City, China, was employed to illustrate its application to communities. The approach and the results of our study demonstrate the ability to extract and understand thematic places from a community perspective. The results of our framework can aid urban planners in designing better urbanization strategies. Highlights: Case study of Wuhan integrates urban road network data and graph embedding methods at a community scale Investigating communities via point-of-interest data and geo-tagged street view images Fusing physical and socioeconomic characteristics extracted from multi-sources of geospatial data to investigate urban vibrancy