Abstract Deep learning methods are emerging as popular computational tools for solving forward and inverse problems in traffic flow. In this paper, we study a neural operator framework for learning solutions to first-order macroscopic traffic flow models with applications in estimating traffic densities for urban arterials. In this framework, an operator is trained to map heterogeneous and sparse traffic input data to the complete macroscopic traffic density in a supervised learning setting. We chose a physics-informed Fourier neural operator ( π -FNO) as the operator, where an additional physics loss based on a discrete conservation law regularizes the problem during training to improve the shock predictions. We also propose to use training data generated from random piecewise constant input data to systematically capture the shock and rarefaction solutions of certain macroscopic traffic flow models. From experiments using the LWR traffic flow model, we found superior accuracy in predicting the density dynamics of a ring-road network and urban signalized road. We also found that the operator can be trained using simple traffic density dynamics, e.g., consisting of 2 3 vehicle queues and 1 2 traffic signal cycles, and it can predict density dynamics for heterogeneous vehicle queue distributions and multiple traffic signal cycles ( 2 ) with an acceptable error. The extrapolation error grew sub-linearly with input complexity for a proper choice of the model architecture and training data. Adding a physics regularizer aided in learning long-term traffic density dynamics, especially for problems with periodic boundary data.

    Highlights An operator learning framework for learning solutions to macroscopic traffic flow models. A unified framework for handling forward and inverse problems is presented. A mechanism for selecting training inputs with superior generalization performance. Extensive experiments quantifying out-of-sample errors and transfer learning performance.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Fourier neural operator for learning solutions to macroscopic traffic flow models: Application to the forward and inverse problems




    Erscheinungsdatum :

    2024-01-29




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Description of Macroscopic Relationships Among Traffic Flow Variables Using Neural Network Models

    Nakatsuji, T. / Tanaka, M. / Nasser, P. et al. | British Library Conference Proceedings | 1995



    Macroscopic Traffic Flow Models: A Question of Order

    Lebacque, J. P. / Lesort, J. B. | British Library Conference Proceedings | 1999