Assessing Traffic's Impact on Urban Heat Islands: An Agent-Based Approach Using Real-World and Simulated Data

Aygun Ismayilova, Manon Prédhumeau

Keywords: Agent-Based Modelling, MATSim Simulation, Urban Climate, Real-World Data, Synthetic Population

Abstract: Urban Heat Islands (UHIs) — where cities are significantly warmer than surrounding rural areas — are driven by urbanization and human activities, including road traffic. Understanding traffic-UHI interactions requires high-resolution spatio-temporal data to capture the local and dynamic characteristics of both systems. While urban temperature sensors are increasingly deployed, fine-scale traffic data remain difficult to obtain and are lacking in most cities. To address this gap, we propose a framework combining MATSim-based traffic simulated data and real-world open data. A synthetic population is used to generate individual vehicular trips, which are then validated against observed traffic data. The approach integrates outputs from multi-agent traffic simulation, with urban structure and land-use variables, as well as meteorological measurements, for a full spatio-temporal analysis. Results suggest diurnal and seasonal patterns in traffic–temperature relationships, highlighting the need to capture dynamic human–environment interactions in UHI research. This study shows how combining simulated and real-world data can enhance our understanding of traffic-induced heat effects.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 13