Artificial Intelligence for Sustainable Urban Mobility: Participatory Training Model in Latin American Intermediary Cities

Abstract

Intermediate cities in Latin America face structural mobility challenges linked to socio-spatial inequality, informal transportation systems, climate vulnerability, and infrastructure deficits. Although Artificial Intelligence (AI) has demonstrated significant potential for optimizing sustainable urban systems, its structured integration into higher education curricula in engineering and urban planning remains limited. This paper presents the conceptual design of the AI-MUS model (Artificial Intelligence – Mobility Urban Sustainability), a pedagogical architecture integrating data science, participatory data collection, predictive modeling, spatial segmentation, generative optimization, and climate resilience modeling under a Latin American contextual framework. A Design-Based Research approach is adopted in its conceptual phase, structuring a replicable methodological framework prepared for future quasi-experimental validation. The model addresses the need for adapted indicators for intermediate Latin American cities and strengthens data literacy for sustainable urban mobility decision-making.