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

2026-02-05

AI Summary

This work proposes a Geographic-Aware Transformer for Traffic Flow prediction (GATTF) to address the challenges posed by the complex spatiotemporal dynamics and nonlinear variations in urban freeway traffic. GATTF uniquely integrates a mutual information–based geographic relationship modeling mechanism into the Transformer architecture, effectively capturing spatial dependencies among sensors without increasing model complexity. By jointly leveraging spatiotemporal sequence modeling and mutual information–driven geographic awareness, the model significantly enhances prediction accuracy and provides highly reliable, forward-looking traffic state data for digital twin systems. Experimental results on real-world traffic data from Geneva’s freeway network demonstrate that GATTF outperforms standard Transformer models and other baseline approaches.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

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.

Problem

• traffic forecasting
• digital twin
• spatio-temporal complexity
• urban motorway
• geographical awareness

Innovation

• Geographically-aware
• Transformer
• Mutual Information
• Traffic Forecasting
• Digital Twin