𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗳𝗼𝗿 𝗠𝗮𝗰𝗿𝗼𝘀𝗰𝗼𝗽𝗶𝗰 𝗧𝗿𝗮𝗳𝗳𝗶𝗰 𝗠𝗼𝗱𝗲𝗹𝗶𝗻𝗴 𝗮𝗻𝗱 𝗢𝗽𝘁𝗶𝗺𝗶𝘇𝗮𝘁𝗶𝗼𝗻

𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗣𝗮𝗽𝗲𝗿𝘀

𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗳𝗼𝗿 𝗠𝗮𝗰𝗿𝗼𝘀𝗰𝗼𝗽𝗶𝗰 𝗧𝗿𝗮𝗳𝗳𝗶𝗰 𝗠𝗼𝗱𝗲𝗹𝗶𝗻𝗴 𝗮𝗻𝗱 𝗢𝗽𝘁𝗶𝗺𝗶𝘇𝗮𝘁𝗶𝗼𝗻

𝗝𝗼𝘂𝗿𝗻𝗮𝗹:
Transportmetrica B: Transport Dynamics

𝗣𝘂𝗯𝗹𝗶𝘀𝗵𝗲𝗿:
Taylor & Francis Group

𝗠𝗮𝗻𝘂𝘀𝗰𝗿𝗶𝗽𝘁 𝗗𝗲𝗮𝗱𝗹𝗶𝗻𝗲:
15 April 2027

𝗔𝗯𝗼𝘂𝘁 𝘁𝗵𝗲 𝗦𝗽𝗲𝗰𝗶𝗮𝗹 𝗜𝘀𝘀𝘂𝗲

Macroscopic traffic models are widely used to analyse traffic dynamics across large spatial and temporal scales. By abstracting from individual vehicle interactions, these models provide computationally efficient and analytically powerful tools for network-level traffic analysis. Their ability to balance simplicity and explanatory power makes them particularly valuable for large-scale transportation planning, infrastructure design, traffic management, and policy development.

However, traditional statistical methods used for model calibration often limit the reliability, adaptability, and predictive capabilities of macroscopic traffic models in complex real-world environments. Recent advances in machine learning and data analytics offer new opportunities to overcome these limitations.

This Special Issue seeks to explore how data-driven approaches and machine learning techniques can complement, enhance, and transform conventional macroscopic traffic models. The integration of machine learning with traffic modelling has the potential to improve predictive accuracy, enhance model robustness, enable real-time optimization, and broaden practical applications ranging from transportation planning and infrastructure management to intelligent transportation systems and connected vehicle ecosystems.

The Special Issue welcomes theoretical, methodological, and applied contributions that advance machine learning-driven macroscopic traffic modelling and demonstrate their value in addressing contemporary transportation challenges.

𝗧𝗼𝗽𝗶𝗰𝘀 𝗼𝗳 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁

Submissions may address, but are not limited to:

• Generalizable macroscopic traffic modelling frameworks
• Network partitioning, classification, and clustering for scalable modelling
• Probe-based data fusion and traffic state estimation
• Self-calibrating macroscopic simulation models
• Explainable Artificial Intelligence (XAI) for macroscopic traffic modelling
• Uncertainty quantification in traffic modelling and forecasting
• Integration of machine learning with traffic simulation platforms
• Data assimilation and imputation methods for large-scale traffic analysis
• Macroscopic impact assessment of Connected and Automated Vehicles (CAVs)
• Centralized and decentralized cooperative control strategies for CAVs
• Traffic optimization and control using connected vehicle data
• Dynamic congestion pricing using predictive traffic models
• Real-time adaptive lane management strategies
• Real-time traffic prediction, management, and control systems
• Demand management and staggered work-hour scheduling for congestion mitigation
• Parking design and pricing policies as demand management tools
• Integration of macroscopic traffic models with energy consumption and emission analysis

𝗦𝗽𝗲𝗰𝗶𝗮𝗹 𝗜𝘀𝘀𝘂𝗲 𝗙𝗼𝗰𝘂𝘀

This Special Issue aims to bring together researchers and practitioners working at the intersection of transportation engineering, machine learning, and intelligent transportation systems. It seeks to advance theoretical foundations, methodological innovations, and real-world applications of machine learning-enhanced macroscopic traffic models, particularly in the areas of traffic prediction, optimization, congestion management, and sustainable mobility solutions.

𝗦𝘂𝗯𝗺𝗶𝘀𝘀𝗶𝗼𝗻 𝗚𝘂𝗶𝗱𝗲𝗹𝗶𝗻𝗲𝘀

• Submission opening date: 15 November 2025.
• Final manuscript submission deadline: 15 October 2026.
• Special Issue completion date: 15 April 2027.
• Manuscripts should present original theoretical, methodological, or applied contributions related to machine learning and macroscopic traffic modelling.
• All submissions will undergo the journal's standard peer-review process.
• Authors should consult the journal's submission guidelines before manuscript submission.

𝗦𝗽𝗲𝗰𝗶𝗮𝗹 𝗜𝘀𝘀𝘂𝗲 𝗘𝗱𝗶𝘁𝗼𝗿𝘀

Mahyar Amirgholy
Kennesaw State University
Email: mahyar.amirgholy@kennesaw.edu

Lukas Ambühl
ETH Zürich
Email: lukas.ambuehl@ivt.baug.ethz.ch

Sergio Batista
Technical University of Lisbon (Instituto Superior Técnico)
Email: sergio.batista@tecnico.ulisboa.pt

𝗣𝗼𝘀𝘁𝗲𝗱 𝗼𝗻 𝗦𝗲𝗿𝘃𝗶𝗰𝗲𝗦𝗲𝘁𝘂 𝗔𝗰𝗮𝗱𝗲𝗺𝗶𝗰𝘀 — 𝗣𝗿𝗲𝗺𝗶𝗲𝗿 𝗣𝗹𝗮𝘁𝗳𝗼𝗿𝗺 𝗳𝗼𝗿 𝗔𝗰𝗮𝗱𝗲𝗺𝗶𝗰 𝗢𝗽𝗽𝗼𝗿𝘁𝘂𝗻𝗶𝘁𝗶𝗲𝘀 & 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗖𝗼𝗹𝗹𝗮𝗯𝗼𝗿𝗮𝘁𝗶𝗼𝗻

Visit official website of the publisher