GEOGRAPHICAL RESEARCH ›› 2021, Vol. 40 ›› Issue (1): 230-246.doi: 10.11821/dlyj020190849

• Articles • Previous Articles     Next Articles

Urban polycentric recognition and spatial interaction analysis based on word vector data field trajectory gravity

LI Xin()   

  1. College of Resource and Environment, Collaborative Innovation Center of Urban-Rural Coordinated Development in Henan, Henan University of Economics and Law, Zhengzhou 450046, China
  • Received:2019-09-30 Accepted:2020-04-21 Online:2021-01-10 Published:2021-03-10


Polycentric structure is an important method of dispersing urban population, relieving traffic congestion, adjusting the imbalance of job-housing, and dealing with "big city disease". First of all, word vector is used to describe the spatial characteristics and behavior rules of the trajectory big data, and vector operation is used to reflect the correlation between the origin points and destination points of the trajectories. In addition, the spatial grid of Zhengzhou city is divided, the gravity of grid units to mobile targets is measured by using the gravitational model of data field theory, and the recognition of polycentric structure is completed. At last, the interaction rules of the polycentric structure are explored with the assistance of the complex network theory, and the relationships between the polycentric nodes are reflected by the in-and-out intensity, net flow ratio and chain weight. The results show that: (1) The gravity strength of trajectories presents a circular spatial pattern with a strong core and weak peripheries, and the region with high gravity spreads along the main roads. There are significant differences in the unbalanced gravity of trajectories among the identified 21 centers. Urban elements and moving targets spread from the saturated core urban area to the periphery along the main traffic routes. The spatial distribution of polycentric structure presents a typical overflow pattern of dense inside and sparse outside. (2) The regional gravity intensity and interaction frequency of the peripheral sub-centers are low, and the interaction direction mainly goes towards the primary centers in the core urban area. Although the planning prospect of the peripheral centers is broad, due to the late planning, remote location and insufficient supporting facilities, their attraction to the surrounding areas is limited. And it will take a long time to achieve the planning objectives. In order to make the sub-centers decentralize better, it is necessary to strengthen the overall planning and guide the scientific development of the sub-centers. A polycentric structure recognition method and spatial interaction analysis method based on the trajectory gravity of word vector data field are proposed. The trajectory word vector describes the spatial information and travel pattern information in a comprehensive way, the trajectory gravity intensity expressed by the potential value of data field is more accurate, and the polycentric spatial interaction structure analyzed in a complex network is clearer. The evolution mechanism of polycentric structure is presented from the perspective of flow. This is a more suitable polycentric analysis method for trajectory data, which provides a new idea for urban planning.

Key words: word vector, data field, polycentric, spatial interaction, trajectory