Spatial-Temporal Inference of Urban Traffic Emissions Based on Taxi Trajectories and Multi-Source Urban Data

09/28/2018 ∙ by Jielun Liu, et al. ∙ 0

Vehicle trajectory data collected via GPS-enabled devices have played increasingly important roles in estimating network-wide traffic, given their broad spatial-temporal coverage and representativeness of traffic dynamics. This paper exploits taxi GPS data, license plate recognition (LPR) data and geographical information for reconstructing the spatial and temporal patterns of urban traffic emissions. Vehicle emission factor models are employed to estimate emissions based on taxi trajectories. The estimated emissions are then mapped to spatial grids of urban areas to account for spatial heterogeneity. To extrapolate emissions from the taxi fleet to the whole vehicle population, we use Gaussian process regression models supported by geographical features to estimate the spatially heterogeneous traffic volume and fleet composition. Unlike previous studies, this paper utilizes the taxi GPS data and LPR data to disaggregate vehicle and emission characteristics through space and time in a large-scale urban network. The results of a case study in Hangzhou, China, reveal high-resolution spatiotemporal patterns of traffic flows and emissions and identify emission hotspots at different locations. This study provides an accessible means of inferring the environmental impact of urban traffic with multi-source data that are now widely available in urban areas.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 13

page 19

page 20

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.