Domain Adaptation Framework for Turning Movement Count Estimation with Limited Data

2025-03-25

AI Summary

Accurate turning movement count (TMC) estimation remains challenging due to scarce labeled data and poor cross-intersection generalization. Method: This paper introduces domain adaptation (DA) into traffic flow modeling for the first time, proposing a few-shot, cross-intersection knowledge transfer framework that jointly leverages traffic controller events, road network topology, and point-of-interest (POI) data. The approach integrates traffic event sequence encoding, graph-structured representation learning, and DA-driven regression to enable robust TMC estimation under zero- or few-shot supervision. Contribution/Results: Evaluated on real-world measurements from 30 intersections in Tucson, the method achieves statistically significant improvements in MAE and RMSE over existing state-of-the-art methods, demonstrating both superior accuracy and strong generalization capability under data-scarce conditions.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Application Domains: Transportation
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Urban transportation networks are vital for the efficient movement of people and goods, necessitating effective traffic management and planning. An integral part of traffic management is understanding the turning movement counts (TMCs) at intersections, Accurate TMCs at intersections are crucial for traffic signal control, congestion mitigation, and road safety. In general, TMCs are obtained using physical sensors installed at intersections, but this approach can be cost-prohibitive and technically challenging, especially for cities with extensive road networks. Recent advancements in machine learning and data-driven approaches have offered promising alternatives for estimating TMCs. Traffic patterns can vary significantly across different intersections due to factors such as road geometry, traffic signal settings, and local driver behaviors. This domain discrepancy limits the generalizability and accuracy of machine learning models when applied to new or unseen intersections. In response to these limitations, this research proposes a novel framework leveraging domain adaptation (DA) to estimate TMCs at intersections by using traffic controller event-based data, road infrastructure data, and point-of-interest (POI) data. Evaluated on 30 intersections in Tucson, Arizona, the performance of the proposed DA framework was compared with state-of-the-art models and achieved the lowest values in terms of Mean Absolute Error and Root Mean Square Error.

Problem

• Estimates turning movement counts with limited data using domain adaptation
• Addresses domain discrepancy in traffic patterns across different intersections
• Improves accuracy over existing models for traffic management

Innovation

• Domain adaptation for traffic count estimation
• Uses event, infrastructure, and POI data
• Outperforms models in accuracy metrics