Dynamic Grid-Based Spatial Density Visualization and Rail Transit Station Prediction

Abstract

The urban rail transit stations are an important part of an urban transit system. Scientific and reasonable location of rail transit station can greatly alleviate traffic pressure. The number of people in the surrounding area of a rail transit station is an important factor for site selection. However, it is difficult to obtain the spatial distribution of population, which brings great difficulties in terms of site selection. Due to the large-scale popularization of AP (Access Point) in China, the spatial distribution of AP is used instead of population distribution to assist site selection. Therefore, a density visualization method based on a dynamic grid is proposed, which can help decision-makers intuitively see the AP density of the uncovered grid of rail transit stations, and then cluster the AP density of the uncovered area to predict the location of new rail transit stations. The validity of the proposed method is demonstrated by using the AP dataset and rail transit data of Beijing in 2013. The results show that our method has high accuracy in predicting the location of rail transit stations. It can provide data support for urban traffic development and management.