Urban mobility system

Original title: Sistema de movilidad urbana

Megacities metropolitan areas with more than 10 million inhabitants face critical challenges driven by high population density, rapid urban expansion, and the complexity of managing infrastructure and services. In these environments, urban freight logistics is heavily impacted by traffic congestion, the diverse needs of residents, businesses, and government, and the growing pressure to reduce CO₂ emissions and environmental impacts. As a result, megacities require advanced, data-informed logistics planning and greener operational strategies.

This thesis presents the “Urban Mobility System” research project, whose main objective is to bring together the general public, the private sector, government, and academia to design better urban freight transportation policies in the context of megacities. The project leverages artificial intelligence and big data to improve operational efficiency, reduce costs, and minimize environmental impact, while also aiming to produce a replicable model that can be applied to other megacities.

The study focuses on selecting a specific area for a logistics assessment, analyzing relevant operational data, and developing performance indicators to measure logistics efficiency. It further evaluates data to capture both public and private sector requirements and generates actionable insights to support policy design and decision-making. The proposed system is implemented as a geospatial data visualization platform centered on a one-square-kilometer logistics zone, enabling detailed views of vehicle flow, stops, and deliveries through heatmaps and reference points. Key metrics, such as distance traveled, travel time, delivery time, and CO₂ emissions, are analyzed, and predictive algorithms are used to identify optimal locations for loading and unloading bays. Overall, the work contributes a scalable, data-driven decision-support approach to improve urban freight operations and sustainability in megacities.