基于时空地理加权回归的服务区驶入量影响因素分析

为掌握河北省服务区驶入量的时空分布规律，构建了时空地理加权回归（geographically and temporally weighted regression，GTWR）模型，揭示了服务区规模、服务区地理区位、关联地区土地利用、高速公路类型等因素在时间和空间上对服务区不同车型驶入量的影响。结果表明：时空地理加权回归模型的拟合结果显著优于最小二乘回归模型与地理加权回归模型；断面交通量对三种车型均具有促进作用，特别是在夏季高温地区服务区对于小型车驶入量促进作用显著；2~4h车程范围内，风景名胜密度对小型车驶入量具有促进作用，且在旅游旺季及位于旅游业发达城市的服务区影响最显著；2~4h车程范围内工商业型信息点(point of information，POI)密度对大中型车驶入量具有促进作用，特别是在货运高峰期及位于商贸发达城市的服务区促进作用显著；所属高速公路沿途资源型城市数量对服务区大型车驶入量具有显著促进作用，特别是在供暖季节。

Analysis of Influencing Factors of Service Area Driving Inlet Based on Geographically and Temporally Weighted Regression

There is an imbalance between supply and demand of parking spaces in the expressway service areas of some areas in Hebei Province. In order to grasp the spatio-temporal distribution of vehicle entry in the service area of Hebei Province, a geographically and temporally weighted regression model was constructed, which revealed the impact of factors such as the scale of the service area, the geographical location of the service area, the socio-economy, the land use of the related areas, and the type of expressway on the driving volume of different models in the service area in time and space. The results show that the fitting results of the geographically and temporally weighted regression model are significantly better than those of the least squares regression model and the geographically weighted regression model. The fitting results of the spatiotemporal geographically weighted regression model were significantly better than those of the least squares regression model and the geographically weighted regression model. The cross-sectional traffic volume has a promoting effect on all three models, especially in the service area of high temperature in summer, which has a significant effect on the driving volume of small cars. Within 2~4h driving range, the density of scenic spots has a promoting effect on the number of small cars, and has the most significant impact in the tourist season and the service areas located in cities with developed tourism. The density of industrial and commercial point of information( POI) within 2~4h driving distance has a promoting effect on the inbound volume of large and medium-sized vehicles, especially during the peak period of freight and in service areas located in cities with developed commerce and trade. The number of resource-based cities along the expressway has a significant effect on the number of large vehicles in the service area, especially during the heating season.