Graph Neural Networks for Traffic Forecasting
See where this sits in the topic map →Summary AI-generated
- TL;DR
- Rapid urbanisation brings significant challenges to urban mobility, which can be addressed through new data-driven methods.
- Problem
- Urban mobility planning, maintenance, and sustainability are increasingly challenged by growing world populations and urbanization, even as computing capabilities and sensor data expand.
- Method
- This work reviews the recent development and application of Graph Neural Networks (GNNs), a class of deep learning methods that process graph-structured data directly, focusing on their use in traffic forecasting.
- Results
- By leveraging the spatial dependencies of traffic data and the power of deep learning, GNN approaches produce state-of-the-art results in traffic forecasting.
- Contributions
- The paper introduces and reviews the emerging topic of GNNs, exploring common variants, different ways to model traffic forecasting as a temporal graph, and approaches for combining graph and temporal learning components.
- Limitations
- The study addresses current limitations in the field as part of its comprehensive review of research opportunities.
- Takeaways
- GNNs offer a powerful framework for traffic forecasting by effectively capturing the spatial and temporal dependencies inherent in urban traffic data.
- Applications
- Traffic forecasting and urban mobility planning.
- Topics
- Graph Neural Networks; Traffic Forecasting; Deep Learning; Urban Mobility
- For industry
- Transportation and urban infrastructure management.
- Why it matters
- Not specified in the abstract.
Abstract
The significant increase in world population and urbanisation has brought several important challenges, in particular regarding the sustainability, maintenance and planning of urban mobility. At the same time, the exponential increase of computing capability and of available sensor and location data have offered the potential for innovative solutions to these challenges. In this work, we focus on the challenge of traffic forecasting and review the recent development and application of graph neural networks (GNN) to this problem. GNNs are a class of deep learning methods that directly process the input as graph data. This leverages more directly the spatial dependencies of traffic data and makes use of the advantages of deep learning producing state-of-the-art results. We introduce and review the emerging topic of GNNs, including their most common variants, with a focus on its application to traffic forecasting. We address the different ways of modelling traffic forecasting as a (temporal) graph, the different approaches developed so far to combine the graph and temporal learning components, as well as current limitations and research opportunities.