Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Forecasting

Traffic forecasting on road networks is a complicated and practically important task that has recently attracted significant attention from the machine learning community, with spatiotemporal graph neural networks (GNNs) becoming the most popular approach. The proper evaluation of traffic forecasting methods requires realistic datasets, but current publicly available traffic benchmarks have significant drawbacks, including the absence of information about road connectivity for road graph construction, limited information about road properties, and a relatively small number of road segments that falls short of real-world applications. Further, current datasets mostly contain information about intercity highways with very sparsely located sensors, while city road networks arguably present a more challenging forecasting task due to much denser roads and more complex urban traffic patterns. In this work, we aim to provide a more complete, realistic, and challenging benchmark for traffic forecasting. We release datasets representing the road networks of two major cities, with the largest containing information about almost 100,000 road segments (more than a 10-fold increase relative to existing datasets). Our datasets contain rich road features and provide fine-grained data about both traffic volume and traffic speed, allowing for building more holistic traffic forecasting systems. We show that most current implementations of neural spatiotemporal models for traffic forecasting have problems scaling to datasets of our size. To overcome this issue, we propose an alternative approach to neural traffic forecasting that uses a GNN without a dedicated module for temporal sequence processing, thus achieving much better scalability, while also demonstrating stronger forecasting performance. We hope that our datasets will be actively used for research in traffic forecasting and, more generally, urban computing and smart city development.