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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Does Information on Weather Affect the Performance of Short-Term Traffic Forecasting Models?




    Publication date :

    2011-08-18


    Size :

    10 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    An Improved Model for Short-Term Traffic Forecasting Considering Weather Impacts

    Chen, Xinchao / Qin, Si / Zhang, Jian et al. | ASCE | 2018


    Enhancing Short-Term Traffic Forecasting with Traffic Condition Information

    Turochy, R. E. | British Library Online Contents | 2006



    Enhancing Short-Term Velocity Forecasting Models by Using ML Models and Traffic Patterns Information

    Lira, Cristián / Véjar, Bastián / Ordóñez, Fernando et al. | Springer Verlag | 2021


    Review of spatio-temporal models for short-term traffic forecasting

    Gang, Chang / Shouhui, Wang / Xiaobo, Xiao | IEEE | 2016