Research Article: Identification of urban regions’ functions in Chengdu, China, based on vehicle trajectory data

Date Published: April 29, 2019

Publisher: Public Library of Science

Author(s): Qingke Gao, Jianhong Fu, Yang Yu, Xuehua Tang, David M. Levinson.

http://doi.org/10.1371/journal.pone.0215656

Abstract

Data about human trajectories has been widely used to study urban regions that are attractive to researchers and are considered to be hotspots. It is difficult, however, to quantify the function of urban regions based on the varieties of human behavior. In this research, we developed a clustering method to help discover the specific functions that exist within urban regions. This method applies the Gaussian Mixture Model (GMM) to classify regions’ inflow and trip count characteristics. It regroups these urban regions using the Pearson Correlation Coefficient (PCC) clustering method based on those typical characteristics. Using a large amount of vehicle trajectory data (approximately 1,500,000 data points) in the Chinese city of Chengdu, we demonstrate that the method can discriminate between urban functional regions, by comparing the proportion of surface objects within each region. This research shows that vehicle trajectory data in different functional urban regions possesses different time-series curves, while similar types of functional regions can be identified by these curves. Compared with remote sensing images and other statistical methods which can provide only static results, our research can provide a timely and effective approach to determine an urban region’s functions.

Partial Text

Cities comprise various functional regions. These regions include residential, educational, commercial, industrial, leisure zones, etc. [1]. Functional urban regions have been long noted as an important influence on how we recall, describe, and manage urban regions [2]. With the continuous progress of urbanization, urban areas constantly expand, and the types of functional urban regions became different from what was envisioned in early planning [3]. Understanding the changes in functional urban regions is critical for effective urban development planning, natural resource allocation, and ecosystem management [4]. In order to make better urban plans, it is important for planners to quickly and accurately identify different functional regions and understand their spatial structure within the city [3].

The study area for this research locates is the Chinese city of Chengdu. As the capital of Sichuan province, Chengdu is located in southwest China. It has an area of 14600 square kilometers and has a population of approximately 16 million as of the end of 2017. In addition, Chengdu contains many ethnic groups and has residents from 55 ethnic minority groups. It comprises 11 administrative districts. Chengdu is a commercial logistics center and a comprehensive transportation hub. Its gross domestic product (GDP) exceeded 1300 billion yuan in 2017 and increased by 8.1% in that year compared to 2016. In 2017, there were 4,942,000 motor vehicles, and privately owned vehicles numbered more than 3,982,000. The vehicle trajectories can reflect the daily travel patterns of its residents based on the large amount of traffic. Because citizens mainly travel within the Fourth Ring Road area in Chengdu, we selected the districts within this area as the study area for this research.

In this study, we developed a clustering method to help discover functional urban regions. This method applies GMM to classify regions’ inflow and trip count characteristics, and regroups urban regions using the PCC clustering method based on these typical characteristics. Using Chengdu’s vehicle trajectory data, we demonstrate how the method can differentiate between urban functional regions by comparing the proportion of surface objects in each region. This research shows that vehicle trajectory data in different functional urban regions has different time-series curves while similar types of functional regions can be identified by these curves.

 

Source:

http://doi.org/10.1371/journal.pone.0215656

 

Leave a Reply

Your email address will not be published.