Macroscopic Traffic Modeling Using Probe Vehicle Data: A Machine Learning Approach
Data Science for Transportation · 2024-12 · 6 (3)
DOI: 10.1007/s42421-024-00102-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Data Science for Transportation, online erschienen am 06.08.2024. Verfasst von Ling Jin und 9 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Federal Highway Administration (FHWA) Office of Transportation Policy Studies, Lawrence Berkeley National Laboratory.
Abstract (Originalsprache)
The macroscopic fundamental diagram (MFD) captures an orderly relationship among traffic flow, density, and speed at the network level. It is a simple yet powerful tool for modeling traffic dynamics in large urban networks with broad application in traffic control and management. However, empirically derived MFDs in urban regions require high-resolution traffic data from the network. Having the network flow and vehicular density estimated at the (granular) census tract level using vehicle probe data, we apply machine learning methods to predict the MFDs across U.S. urban areas and capture the impacts of location-specific input features on the network flow–density relationships at a large scale. The results show that, among the four tested machine learning approaches (Random Forest, XGBoost, Support Vector Machine, and Neural Network), XGBoost delivers the best performance in predicting network traffic flow based on vehicular density and location attributes. Using interaction Shapley Additive explanation (SHAP) values and partial correlation analysis, we examine the factors influencing MFD shapes across different locations. Our empirical findings reveal that across U.S. urban areas, network topology, transportation infrastructure, and land use are primary factors shaping MFD curves, while demand and trip-related factors play a lesser role. Specifically, higher ranking roads, centrality, and development levels correlate positively with network capacity and critical density, whereas negative associations are observed for network connectivity, mixed-use development, and road roughness levels.
Förderung
- the Federal Highway Administration (FHWA) Office of Transportation Policy Studies
- Lawrence Berkeley National Laboratory
Zitieren
APA
Jin, L., Xu, X., Wang, Y., Lazar, A., Sadabadi, K. F., Spurlock, C. A., Needell, Z., Don, D. R., Amirgholy, M., & Asudegi, M. (2024). Macroscopic Traffic Modeling Using Probe Vehicle Data: A Machine Learning Approach. Data Science for Transportation, 6(3). https://doi.org/10.1007/s42421-024-00102-4
Vancouver
Jin L, Xu X, Wang Y, Lazar A, Sadabadi KF, Spurlock CA, et al. Macroscopic Traffic Modeling Using Probe Vehicle Data: A Machine Learning Approach. Data Science for Transportation. 2024;6(3). doi:10.1007/s42421-024-00102-4
BibTeX
@article{Jin2024,
author = {Jin, Ling and Xu, Xiaodan and Wang, Yuhan and Lazar, Alina and Sadabadi, Kaveh Farokhi and Spurlock, C. Anna and Needell, Zachary and Don, Duleep Rathgamage and Amirgholy, Mahyar and Asudegi, Mona},
title = {Macroscopic Traffic Modeling Using Probe Vehicle Data: A Machine Learning Approach},
journal = {Data Science for Transportation},
year = {2024},
volume = {6},
number = {3},
doi = {10.1007/s42421-024-00102-4}
}
EUVIMED