1. Introduction
Pandemics have long been among the most significant challenges facing urban systems and public health governance. The COVID-19 outbreak once again exposed the vulnerability of metropolitan areas to large-scale health emergencies. High population density, complex transportation networks, and intensive social interactions have made major cities key hotspots for the rapid spread of infectious diseases. Under such conditions, traditional crisis management approaches, which largely rely on reactive measures after an outbreak occurs, have shown serious limitations. In response, urban intelligence has emerged as an advanced stage in the evolution of smart cities, offering new opportunities for predicting, diagnosing, and controlling pandemics. By leveraging technologies such as artificial intelligence (AI), machine learning (ML), the Internet of Things (IoT), big data, and information and communication technologies (ICT), urban intelligence enables the real-time collection, processing, and analysis of urban data and supports more informed decision-making in public health emergencies.
Research Questions
1. How has the role of urban intelligence in pandemic management been conceptualized in the international literature, and how have its key themes evolved over time?
2. What measures and innovations have been implemented within Tehran's urban management system to utilize urban intelligence in responding to the COVID-19 pandemic?

2. Literature Review
Recent studies suggest that urban intelligence has become a key approach to strengthening urban resilience against health crises. Allam et al. (2020) argue that integrating AI, big data, and digital infrastructures can significantly improve cities' capacity to predict and manage pandemics. White and Clarke (2020) describe urban intelligence as a mechanism that transforms real-time urban data into actionable knowledge, while Ali (2024) presents it as a comprehensive framework for pandemic prediction, diagnosis, treatment, and control. In the healthcare sector, Alimadadi et al. (2020), Piccialli et al. (2021), and Lalmuanawma et al. (2020) highlight the role of AI and machine learning in disease diagnosis, medical data analysis, and the efficient allocation of healthcare resources. Similarly, Eum and Kim (2022) and Kostina and Kostina (2022) emphasize the importance of ICT infrastructure, telemedicine, and digital services in reducing physical contact and maintaining urban functions during pandemics. Despite these advances, the application of urban intelligence to pandemic management in Iranian cities, particularly Tehran, remains underexplored.

3. Methodology
This applied study adopted a descriptive-analytical approach and was conducted in two qualitative phases. In the first phase, a theoretical framework was developed through the synthesis of studies related to urban intelligence and pandemic management. Bibliometric analysis and keyword co-occurrence mapping were then carried out using VOSviewer software to identify major research trends and conceptual developments. The dataset consisted of 336 articles published between 2020 and 2025 and selected from the ScienceDirect database based on the PRISMA framework. In the second phase, policy documents, official reports, and measures related to COVID-19 management in Tehran and Iran were examined through qualitative content and text analysis. This stage assessed the use of urban intelligence infrastructures in three areas: outbreak prediction, diagnosis and treatment, and disease containment.
4. Results
The bibliometric analysis revealed that the global literature was organized around nine major thematic clusters. These included technological ecosystems and data infrastructures, digital health and telemedicine, urban resilience and smart cities, intelligent transportation and mobility forecasting, data-driven healthcare systems, smart mental health services, GeoAI applications, epidemic management models, and global health decision-support systems. Concepts such as artificial intelligence, COVID-19, digital health, urban resilience, and smart technologies occupied the most central positions within the knowledge network. The findings also indicated a gradual shift from reactive approaches focused on quarantine and social distancing toward preventive strategies centered on digital health, health equity, and data governance.
The analysis of Tehran's experience showed that the most extensive use of smart technologies occurred in the area of disease control and containment. Major initiatives included online education platforms, vaccination registration systems, monitoring dashboards, the Mask mobile application, the national 4030 consultation service, and integrated health information systems. In the diagnosis and treatment domain, telemedicine services, online consultation platforms, and digital screening tools helped reduce unnecessary in-person visits. However, a substantial gap was identified in the area of outbreak prediction. AI-, ML-, and IoT-based infrastructures capable of early outbreak detection were largely absent, and advanced predictive analytics played only a limited role in urban decision-making.

5. Discussion and Conclusion
The findings suggested that although Tehran successfully utilized ICT-based solutions to manage several aspects of the COVID-19 crisis, it remained distant from a fully developed urban intelligence model. The dominance of communication technologies over analytical systems, weak data integration, limited use of AI and machine learning, and insufficient attention to health equity, privacy, and data governance represented major challenges. Moving from reactive crisis management toward a predictive and proactive model required the development of integrated data-driven infrastructures, stronger connections between urban and healthcare systems, wider adoption of intelligent forecasting tools, and the institutionalization of data-informed governance. Such measures could enhance urban resilience and improve Tehran's preparedness for future pandemics and public health emergencies.