A Geographically and Temporally Weighted Regression Model to Explore the Spatiotemporal Influence of Built Environment on Trip Distribution: A Case Study in Hangzhou

摘要

Trip distribution constitutes an important part of transportation planning. The existing models for trip distribution are mainly based on the gravity model. Time and built environment are critical dimensions that the traditional gravity model cannot recognize when performing trip distribution predictions. This study introduces a geographically and temporally weighted regression (GTWR) model to capture the spatiotemporal influence of built environment on trip distributions and estimates the trip distribution more accurately. Experimental data, the license plate data, and point-of-interest (POI) data in Hangzhou from 2016 is utilized to evaluate the accuracy of the GTWR model at the traffic analysis zone (TAZ) level, which is compared with the estimation accuracy of the gravity model. In particular, based on the estimation results of GTWR model, the spatiotemporal influence of land use features on trip distribution can be analyzed. This article is the first to apply the GTWR model to trip distribution.