Spatio-Temporal Graph Neural Network for Urban Spaces: Interpolating Citywide Traffic Volume

TL;DR

This paper introduces GNNUI, a novel graph neural network approach for urban traffic volume estimation, capable of accurate interpolation even with sparse sensor data, and provides new large-scale urban traffic benchmarks.

Contribution

GNNUI employs a masking algorithm, node features, and a zero-inflated loss function, advancing urban traffic interpolation methods and establishing new benchmark datasets.

Findings

GNNUI outperforms recent interpolation methods across multiple metrics.

The model remains robust with sensor coverage as low as 1%.

Performance degrades minimally as sensor data decreases.

Abstract

Graph Neural Networks have shown strong performance in traffic volume forecasting, particularly on highways and major arterial networks. Applying them to urban settings, however, presents unique challenges: urban networks exhibit greater structural diversity, traffic volumes are highly overdispersed with many zeros, the best way to account for spatial dependencies remains unclear, and sensor coverage is often very sparse. We introduce the Graph Neural Network for Urban Interpolation (GNNUI), a novel urban traffic volume estimation approach. GNNUI employs a masking algorithm to learn interpolation, integrates node features to capture functional roles, and uses a loss function tailored to zero-inflated traffic distributions. In addition to the model, we introduce two new open, large-scale urban traffic volume benchmarks, covering different transportation modes: Strava cycling data from Berlin and New York City taxi data. GNNUI outperforms recent, some graph-based, interpolation methods across metrics (MAE, RMSE, true-zero rate, Kullback-Leibler divergence) and remains robust from 90% to 1% sensor coverage. For example, on the Strava dataset, the MAE increases only from 7.1 to 10.5, and on the Taxi dataset, from 23.0 to 40.4. These results demonstrate that GNNUI maintains strong performance despite extreme data scarcity, a common condition in real-world urban settings. We also examine how graph connectivity choices influence model accuracy.