Geographically-aware Transformer-based Traffic Forecasting for Urban Motorway Digital Twins

TL;DR

This paper presents GATTF, a Transformer-based traffic forecasting model that leverages geographical relationships between sensors to improve accuracy in motorway traffic prediction, validated on real data from Geneva.

Contribution

The paper introduces a geographically-aware Transformer model that uses mutual information to enhance traffic forecasting accuracy without added complexity.

Findings

GATTF outperforms standard Transformer models in accuracy.

Incorporating geographical relationships improves forecast precision.

Model validated on real motorway data from Geneva.

Abstract

The operational effectiveness of digital-twin technology in motorway traffic management depends on the availability of a continuous flow of high-resolution real-time traffic data. To function as a proactive decision-making support layer within traffic management, a digital twin must also incorporate predicted traffic conditions in addition to real-time observations. Due to the spatio-temporal complexity and the time-variant, non-linear nature of traffic dynamics, predicting motorway traffic remains a difficult problem. Sequence-based deep-learning models offer clear advantages over classical machine learning and statistical models in capturing long-range, temporal dependencies in time-series traffic data, yet limitations in forecasting accuracy and model complexity point to the need for further improvements. To improve motorway traffic forecasting, this paper introduces a Geographically-aware Transformer-based Traffic Forecasting GATTF model, which exploits the geographical relationships between distributed sensors using their mutual information (MI). The model has been evaluated using real-time data from the Geneva motorway network in Switzerland and results confirm that incorporating geographical awareness through MI enhances the accuracy of GATTF forecasting compared to a standard Transformer, without increasing model complexity.