Short-term traffic prediction using physics-aware neural networks
Journal article, 2022
In this work, we propose an algorithm performing short-termpredictions of the flow and speed of vehicles on a stretch of road, using past measurements of these quantities. This algorithm is based on a physics-aware recurrent neural network. Adiscretization of a macroscopic traffic flowmodel (using the so-called Traffic Reaction Model) is embedded in the architecture of the network and yields traffic state estimations and predictions for the flow and speed of vehicles, which are physically-constrained by the macroscopic traffic flow model and based on estimated and predicted space-time dependent traffic parameters. These parameters are themselves obtained using a succession of LSTM recurrent neural networks. The algorithm is tested on raw flow measurements obtained from loop detectors.
Macroscopic traffic flow model
LSTM
Traffic reaction model
Traffic prediction
Recurrent neural networks
Author
Mike Pereira
Chalmers, Electrical Engineering, Systems and control
Annika Lang
Chalmers, Mathematical Sciences, Applied Mathematics and Statistics
Balázs Adam Kulcsár
Chalmers, Electrical Engineering, Systems and control
Transportation Research, Part C: Emerging Technologies
0968-090X (ISSN)
Vol. 142 103772STOchastic Traffic NEtworks (STONE)
Chalmers AI Research Centre (CHAIR), -- .
Chalmers, 2020-02-01 -- 2022-01-31.
OPerational Network Energy managemenT for electrified buses (OPNET)
Swedish Energy Agency (46365-1), 2018-10-01 -- 2021-12-31.
IRIS: Inverse Reinforcement-Learning and Intelligent Swarm Algorithms for Resilient Transportation Networks
Chalmers, 2020-01-01 -- 2021-12-31.
Efficient approximation methods for random fields on manifolds
Swedish Research Council (VR) (2020-04170), 2021-01-01 -- 2024-12-31.
Stochastic Continuous-Depth Neural Networks
Chalmers AI Research Centre (CHAIR), 2020-08-15 -- .
Real-Time Robust and AdaptIve Learning in ElecTric VEhicles (RITE)
Chalmers AI Research Centre (CHAIR), 2020-01-01 -- 2021-12-31.
Chalmers, 2020-01-01 -- 2021-12-31.
Areas of Advance
Transport
Subject Categories
Computational Mathematics
Transport Systems and Logistics
Business Administration
DOI
10.1016/j.trc.2022.103772