Network-Level Vehicle Delay Estimation at Heterogeneous Signalized Intersections

2025-10-01

AI Summary

To address the poor generalizability and low accuracy of vehicle delay estimation at heterogeneous signalized intersections—characterized by significant variations in road geometry, signal timing plans, and driving behavior—this paper proposes GBBW, a similarity-based reweighting domain adaptation framework. GBBW jointly optimizes dynamic source-sample reweighting with a gradient-boosting regression model to enable cross-intersection knowledge transfer. It integrates multi-source traffic data, incorporates feature disentanglement for robust representation learning, and employs a few-shot fine-tuning strategy on the target domain. Extensive experiments across 57 real-world intersections demonstrate that GBBW reduces average delay estimation error by 21.3% compared to eight state-of-the-art regression models and seven instance-level domain adaptation methods, while improving estimation stability by 36.7%. The framework significantly enhances model robustness and cross-scenario portability.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate vehicle delay estimation is essential for evaluating the performance of signalized intersections and informing traffic management strategies. Delay reflects congestion levels and affects travel time reliability, fuel use, and emissions. Machine learning (ML) offers a scalable, cost-effective alternative; However, conventional models typically assume that training and testing data follow the same distribution, an assumption that is rarely satisfied in real-world applications. Variations in road geometry, signal timing, and driver behavior across intersections often lead to poor generalization and reduced model accuracy. To address this issue, this study introduces a domain adaptation (DA) framework for estimating vehicle delays across diverse intersections. The framework separates data into source and target domains, extracts key traffic features, and fine-tunes the model using a small, labeled subset from the target domain. A novel DA model, Gradient Boosting with Balanced Weighting (GBBW), reweights source data based on similarity to the target domain, improving adaptability. The framework is tested using data from 57 heterogeneous intersections in Pima County, Arizona. Performance is evaluated against eight state-of-the-art ML regression models and seven instance-based DA methods. Results demonstrate that the GBBW framework provides more accurate and robust delay estimates. This approach supports more reliable traffic signal optimization, congestion management, and performance-based planning. By enhancing model transferability, the framework facilitates broader deployment of machine learning techniques in real-world transportation systems.

Problem

• Addressing poor generalization in vehicle delay estimation models
• Proposing domain adaptation for heterogeneous signalized intersections
• Improving transferability of machine learning across traffic domains

Innovation

• Domain adaptation framework for heterogeneous intersections
• Gradient Boosting with Balanced Weighting reweights data
• Fine-tunes model using small labeled target subset