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. A way to represent traffic data is in the form of temporally changing heatmaps visualizing attributes of traffic, such as speed and volume. In recent works, U-Net models have shown SOTA performance on traffic forecasting from 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.
@article{arxiv.2202.06725,
title = {A Graph-based U-Net Model for Predicting Traffic in unseen Cities},
author = {Luca Hermes and Barbara Hammer and Andrew Melnik and Riza Velioglu and Markus Vieth and Malte Schilling},
journal= {arXiv preprint arXiv:2202.06725},
year = {2022}
}