A Graph-based U-Net Model for Predicting Traffic in unseen Cities

Abstract—Accurate traffic prediction is a key ingredient to enable traffic management like rerouting cars to reduce road congestion or regulating traffic via dynamic speed limits to maintain a steady flow. One way to represent traffic data is as temporally changing heatmaps visualizing attributes of traffic, such as speed and volume. In recent approaches, UNet models have shown state of the art performance on traffic forecasting from such heatmaps. We propose to combine the U-Net architecture with graph layers which improves spatial generalization to unseen road networks compared to a Vanilla U-Net. In particular, we specialize existing graph operations to be sensitive to geographical topology and generalize pooling and upsampling operations to be applicable to graphs.

Download paper here

Cited as:

@article{hermes2022graph,
  title={A Graph-based U-Net Model for Predicting Traffic in unseen Cities},
  author={Hermes, Luca and Hammer, Barbara and Melnik, Andrew and Velioglu, Riza and Vieth, Markus and Schilling, Malte},
  journal={arXiv preprint arXiv:2202.06725},
  year={2022}
}