Smart cities have emerged as a solution to urban challenges such as population growth, air pollution, traffic congestion, and resource depletion. A key component of these cities is intelligent transportation systems, which leverage advanced technologies and big data to enhance the efficiency, sustainability, and accessibility of public transport. This study investigates the integration of smart card data and environmental factors such as weather, air quality, events, and land use in public transportation management in Mashhad, Iran. By applying data mining and machine learning techniques, we develop a data-driven framework capable of identifying travel patterns, predicting demand, and optimizing operational planning. The findings demonstrate that combining smart card data with environmental variables significantly improves prediction accuracy, enabling more data-informed decisionmaking in transport management and urban planning.

Keywords