Highlights This study introduces a new framework named physics regularized machine learning. Macroscopic traffic flow models are encoded into Gaussian Process. The model outperforms classical traffic flow models in capturing data uncertainty. The model is more robust than pure machine learning in dealing with noisy data. The model brings a new insight into machine learning application in transportation.

    Abstract Despite the wide implementation of machine learning (ML) technique in traffic flow modeling recently, those data-driven approaches often fall short of accuracy in the cases with a small or noisy training dataset. To address this issue, this study presents a new modeling framework, named physics regularized machine learning (PRML), to encode classical traffic flow models (referred as physics models) into the ML architecture and to regularize the ML training process. More specifically, leveraging the Gaussian process (GP) as the base model, a stochastic physics regularized Gaussian process (PRGP) model is developed and a Bayesian inference algorithm is used to estimate the mean and kernel of the PRGP. A physics regularizer, based on macroscopic traffic flow models, is also developed to augment the estimation via a shadow GP and an enhanced latent force model is used to encode physical knowledge into the stochastic process. Based on the posterior regularization inference framework, an efficient stochastic optimization algorithm is then developed to maximize the evidence lowerbound of the system likelihood. For model evaluations, this paper conducts empirical studies on a real-world dataset which is collected from a stretch of I-15 freeway, Utah. Results show the new PRGP model can outperform the previous compatible methods, such as calibrated traffic flow models and pure machine learning methods, in estimation precision and is more robust to the noisy training dataset.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Macroscopic traffic flow modeling with physics regularized Gaussian process: A new insight into machine learning applications in transportation


    Beteiligte:
    Yuan, Yun (Autor:in) / Zhang, Zhao (Autor:in) / Yang, Xianfeng Terry (Autor:in) / Zhe, Shandian (Autor:in)


    Erscheinungsdatum :

    2021-02-18


    Format / Umfang :

    23 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Traffic Flow Modeling With Gradual Physics Regularized Learning

    Yuan, Yun / Wang, Qinzheng / Yang, Xianfeng Terry | IEEE | 2022


    Control Oriented Freeway Traffic Modelling by Physics-Regularized Machine Learning

    Binjaku, K. / Mece, E.K. / Pasquale, C. et al. | IEEE | 2023


    Introducing Buses into First-Order Macroscopic Traffic Flow Models

    Lebacque, J.P. / Lesort, J.B. / Giorgi, F. | Transportation Research Record | 1998



    Introducing Buses into First-Order Macroscopic Traffic Flow Models

    Lebacque, J. P. / Lesort, J. B. / Giorgi, F. et al. | British Library Conference Proceedings | 1998