Delineating urban job-housing patterns at a parcel scale with street view imagery

ABSTRACT

Empirical data are limited to decipher where people live and work in large cities; however, neighborhood information, such as street view image, is rich and abundant. We construct a ResNet-50-based social detection model to explore the potential relationship between street view images and job-housing attributes. The method extracts street view images of a neighborhood in all eight directions to predict land parcels’ job-housing attributes and uses an entropy index to measure the degree of job-housing mixture in Shenzhen as an example. The social-detection model performs well with a low RMSE (0.1094) in identifying job-housing patterns. The eight-direction neighborhood method shows the best support for sufficient neighborhood information from street view images (RMSE = 0.1135) compared with other neighborhood methods. This study demonstrates the feasibility of using street-view images and deep learning to characterize job-housing attributes consistent with findings from urban studies with socioeconomic data; for example, the research finding concurs that Shenzhen has many high job-housing mixtures with very few areas designated for jobs or residences. The proposed method, when applied regularly, can help monitor spatial dynamics of urban job-housing patterns to inform city planning and development.

KEYWORDS:

• Urban spatial structure
• job-housing
• street view images
• deep learning
• socioeconomic characteristics

Acknowledgments

Thanks to the editor and three anonymous reviewers for their careful work and detailed suggestions. We are also grateful to Starbucks, located on the first floor of the New Development International Center Building in Optics Valley, Wuhan, for providing a place to work and discuss the study and the patience of its staff.

Data availability statement

The data and codes that support the findings of the present study are available on Figshare at https://doi.org/10.6084/m9.figshare.12960212.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by the National Key Research and Development Program of China [2019YFB2102903], the National Natural Science Foundation of China [41801306, 41671408].

Notes on contributors

Yao Yao

Yao Yao is currently an Associate Professor in the School of Geography and Information Engineering at China University of Geosciences (Wuhan). His research focuses on geospatial big data mining and urban computing.

Jiaqi Zhang

Jiaqi Zhang is a master candidate in the School of Geography and Information Engineering at China University of Geosciences (Wuhan). Her research focuses on street-view analysis, spatial analysis and urban computing.

Chen Qian

Chen Qian is a Ph.D. candidate in the School of Engineering and Applied Science at the University of Virginia. His research focuses on data mining and geographical information science.

Yu Wang

Yu Wang is an undergraduate student in the School of Geography and Information Engineering at China University of Geosciences (Wuhan). His major is software engineering.

Shuliang Ren

Shuliang Ren is a master candidate in the School of Geography and Information Engineering at China University of Geosciences (Wuhan). His research focuses on data mining and social computing.

Zehao Yuan

Zehao Yuan is a Ph.D. candidate in the State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing at Wuhan University. His research focuses on trajectory data mining and spatial analysis.

Qingfeng Guan

Qingfeng Guan is a Professor in the School of Geography and Information Engineering at China University of Geosciences (Wuhan). His research focuses on high-performance spatial intelligent computing and urban modeling.