Data-Driven Models for Traffic Flow at Junctions

TL;DR

This paper introduces a novel data-driven approach using neural networks to model traffic flow at junctions, ensuring consistency with hyperbolic conservation laws and improving prediction accuracy in traffic network simulations.

Contribution

It develops a new class of neural network-based models that incorporate the solution space of the half-Riemann problem for traffic junctions, aligning with macroscopic traffic models.

Findings

Models accurately predict traffic flow at junctions.

Data-driven models outperform traditional ad-hoc models.

Numerical results show improved boundary condition estimation.

Abstract

The simulation of traffic flow on networks requires knowledge on the behavior across traffic intersections. For macroscopic models based on hyperbolic conservation laws there exist nowadays many ad-hoc models describing this behavior. Based on real-world car trajectory data we propose a new class of data-driven models with the requirements of being consistent to networked hyperbolic traffic flow models. To this end the new models combine artificial neural networks with a parametrization of the solution space to the half-Riemann problem at the junction. A method for deriving density and flux corresponding to the traffic close to the junction for data-driven models is presented. The models parameter are fitted to obtain suitable boundary conditions for macroscopic first and second-order traffic flow models. The prediction of various models are compared considering also existing coupling rules at the junction. Numerical results imposing the data-fitted coupling models on a traffic network are presented exhibiting accurate predictions of the new models.