Analysis of influencing factors on urban traffic congestion and prediction of congestion time based on spatiotemporal big data

Abstract

In recent years, with the acceleration of urbanization, the number of motor vehicles in China has increased dramatically. Traffic congestion and urban disease are increasingly prominent, which to some extent limits the development of the national economic level. In this study, we take the five urban areas in the center of Chengdu as an example, use Python crawler to mine the data that can help to study the influencing factors of urban traffic congestion from the 1.4 billion GPS records of taxis in Chengdu, the road traffic flow and POI data crawled on the open platform of AMAP, and then establish the principal component analysis, grey correlation analysis and neural network prediction model to find out the impact of traffic congestion and the main factors of the problem. Finally, we found that seven indicators, such as time period, the number of traffic lights, road width and traffic volume, have significant impact on road traffic congestion, and predicted traffic congestion through BP neural network.