Abstract Although weather, traffic mix and speed variability across lanes are largely considered as significant determinants of traffic flow characteristics on freeways, they have not been incorporated into short-term traffic forecasting models. We evaluate the effects of weather and traffic mix on the predictability of traffic speed using several vector autoregressive moving average models with exogenous variables. Results indicate that including exogenous variables in the forecasting models only marginally improves their prediction performance, while modeling innovations such as Vector and Bayesian estimation improves the models significantly.
Does Information on Weather Affect the Performance of Short-Term Traffic Forecasting Models?
2011-08-18
10 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Enhancing Short-Term Traffic Forecasting with Traffic Condition Information
British Library Online Contents | 2006
|Enhancing Short-Term Traffic Forecasting with Traffic Condition Information
Online Contents | 2006
|Short-Term Forecasting of Traffic Volume
Transportation Research Record | 2013
|