Identifying Urban Functional Zones Using Public Bicycle Rental Records and Point-of-Interest Data

Xiaoyi Zhang,Renyi Liu,Feng Zhang,Zhenhong Du,Wenwen Li

doi:10.3390/ijgi7120459

Xiaoyi Zhang, Renyi Liu + Show 3 more

Open Access

https://doi.org/10.3390/ijgi7120459

Copy DOI

Abstract

Human mobility data have become an essential means to study travel behavior and trip purpose to identify urban functional zones, which portray land use at a finer granularity and offer insights for problems such as business site selection, urban design, and planning. However, very few works have leveraged public bicycle-sharing data, which provides a useful feature in depicting people’s short-trip transportation within a city, in the studies of urban functions and structure. Because of its convenience, bicycle usage tends to be close to point-of-interest (POI) features, the combination of which will no doubt enhance the understanding of the trip purpose for characterizing different functional zones. In our study, we propose a data-driven approach that uses station-based public bicycle rental records together with POI data in Hangzhou, China to identify urban functional zones. Topic modelling, unsupervised clustering, and visual analytics are employed to delineate the function matrix, aggregate functional zones, and present mixed land uses. Our result shows that business areas, industrial areas, and residential areas can be well detected, which validates the effectiveness of data generated from this new transportation mode. The word cloud of function labels reveals the mixed land use of different types of urban functions and improves the understanding of city structures.

Highlights

Urban functional zones are the areas assigned to different social and economic activities
The analysis framework we propose for the identification of urban functional zones from bicycle rental records and POI data have two steps: (1) topic modelling and (2) semantic annotation
A possible explanation may be that people tend to use the bicycles to commute to the office in the morning instead of going home, since the time limitation is much looser at night and allows for more travel choices such as walking

Summary

Introduction

Urban functional zones are the areas assigned to different social and economic activities. The majority of scientists take advantage of human mobility data such as taxi trajectories [7], mobile trace data [8,9] and check-in data on social media [10] to gather information about place and model urban structure. These studies perform well in understanding the human activities that occur in space and demonstrate the correlation between travel patterns and urban functions [6]

Methods

Results

Discussion

Conclusion