Short-term traffic prediction using physics-aware neural networks
This work addresses traffic management by improving prediction accuracy for road vehicle flux, though it appears incremental as it combines existing models with neural networks.
The authors tackled short-term traffic flux prediction by embedding a discretized macroscopic traffic flow model into a physics-aware recurrent neural network, which also provides physically-constrained smoothing of input data.
In this work, we propose an algorithm performing short-term predictions of the flux of vehicles on a stretch of road, using past measurements of the flux. This algorithm is based on a physics-aware recurrent neural network. A discretization of a macroscopic traffic flow model (using the so-called Traffic Reaction Model) is embedded in the architecture of the network and yields flux predictions based on estimated and predicted space-time dependent traffic parameters. These parameters are themselves obtained using a succession of LSTM ans simple recurrent neural networks. Besides, on top of the predictions, the algorithm yields a smoothing of its inputs which is also physically-constrained by the macroscopic traffic flow model. The algorithm is tested on raw flux measurements obtained from loop detectors.