AI for Cities: Driving Advanced Urban Efficiency, Quality of Life, and Resiliency

2026-03-17

Guest Editors
Dr. José Antonio Ondiviela, Universidad Francisco de Vitoria
Dra. María Barco Antón, Universidad CEU San Pablo.
Dr. Joaquín Sotelo González, Universidad Complutense de Madrid

Abstract
Across the globe, cities are grappling with the dual challenge of sustaining growth while ensuring an improved quality of life for their citizens. Technological innovations—particularly in the realm of Artificial Intelligence (AI)—are revolutionizing how urban environments are planned, managed, and experienced. The integration of advanced technologies such as Generative AI, Digital Twin Simulators, and Agentic AI is transforming urban environments, enhancing urban efficiency, quality of life, and resilience. These technologies offer innovative solutions to address the challenges posed by rapid urbanization, resource depletion, and environmental sustainability. From Generative AI models that design optimal information management solutions and citizen engagement to Digital Twin Simulators that replicate real world conditions in virtual space to help managers make the best-informed decisions, and on to Agentic AI systems capable of semi autonomous decision-making helping our civil servants with complex task, these advancements open up new frontiers in urban innovation.

Generative AI is not only being utilized to enhance information management and citizen services but also urban planning and governance by enabling anticipation and simulation. This involves using AI to predict future urban scenarios and inform policy-making, as seen in the development of city brains that manage urban domains like transport and safety through large-scale AI platforms (Cugurullo & Xu, 2024). Additionally, Generative AI is integrated into Urban Digital Twin (UDT) frameworks to improve predictive analytics and simulators, as demonstrated by the Large Flow Model (LFM) which models urban flows to support sustainable urban environments (Huang et al., 2025).

Digital Twins, virtual replicas of urban environments, are crucial for real-time monitoring and simulation of urban systems. They enable cities to adapt to challenges by providing a platform for testing scenarios and identifying bottlenecks, thus enhancing urban efficiency and resilience (Gkontzis et al.,2024). AI-powered Digital Twins, when combined with IoT, optimize energy use and enhance resilience in urban contexts, contributing significantly to sustainability (Alnaser et al., 2024). In smart city infrastructure, AI-enhanced Digital Twins have been shown to improve energy efficiency and reduce carbon footprints, demonstrating their potential in reshaping city planning and resource consumption (Li, 2025). In the physical city (based on IoT data) we can use Digital twins to test potential solutions to any given problem, then choose the best in terms of efficiency, cost, time-to-deliver and low citizens’ life disruption.

Agentic AI’s go beyond language generation (LLM) to actionable urban tasks. These agents simulate complex urban systems and provide a multidisciplinary approach to managing urban complexity, addressing issues such as traffic congestion and pollution (Xu et al., 2023). This approach signifies a transformative step in urban intelligence, harnessing AI to unravel and address the intricate dynamics of urban systems. Agentic AI’s can pre-process massive amount of info, docs, etc preparing administrative tasks for final human-in-the- loop decisions, boosting efficiency.

Despite the advancements, challenges remain in integrating these technologies into practical urban solutions.

In conclusion, the integration of Generative AI, Digital Twin Simulators, and Agentic AI is pivotal in advancing city efficiency, quality of life, and resilience. These technologies offer innovative solutions for sustainable urban development, though challenges remain in their practical implementation and integration. Continued research and development are essential to overcome these challenges and harness the full potential of these technologies in creating advanced, sustainable cities.

Such AI-driven frameworks can yield significant improvements in efficiency, resiliency, and overall quality of life. They enable city managers and policymakers to make proactive, data informed decisions, predict and respond to changing conditions, and foster inclusive, citizen centric development.

In the current climate of emerging and adopting new technologies, with a dizzying acceleration of new announcements and possibilities, especially in the field of applied AI, cities need to incorporate these innovations to improve the quality of service to their citizens and their attractiveness to talent and investors. Due to the long and complex public contracting processes, they need to seek out the most advanced, most recently developed systems. Nor can they wait for these new developments to become commercial products (this would add extra months to the solutions age, rendering it almost obsolete). The only solution is to explore the latest technology, the latest proposals, “what's cooking in the oven, then prepare the table”. That is the reason we are holding this call: to connect cities with the leading-edge newest technologies in AI, directly from the innovation lab.

To further accelerate this knowledge exchange and practical impact, this monographic issue seeks to bring together groundbreaking research from universities, research institutes, start-ups and companies experimental department, especially those projects that have reached minimum a Technology Readiness Level of 5 (TRL5)—indicating validated prototypes or pilot implementations in real-world contexts but not reaching yet the category of commercially available products.

Potential Research Goals

1. Urban Efficiency and Optimization

  • Harnessing AI (Generative, Agentic, or otherwise) to improve public service efficiency, utilities management, traffic control, sustainability, and infrastructure maintenance.
  • Leveraging digital twins for real-time operational insights, predictive analytics and solutions to problems simulation and virtual testing.

2. Quality of Life Enhancements

  • Integrating AI-driven solutions to improve social services delivery, public health, and environmental changes impact.
  • Demonstrating how AI-based services can enhance everyday experiences and citizen engagement for diverse city populations,
    always with citizen front and ahead of all service proposals.

3. Resiliency and Sustainability

  • Using digital twin simulations and AI to anticipate, model, and mitigate climate-related risks or infrastructural potential failures. Improve physical and social resiliency.
  • Exploring adaptive frameworks that help cities maintain stability and continuity under various stressors.

4. Ethics, Governance, and Socioeconomic Impact

  • Addressing regulatory requirements, equitable data governance, and privacy considerations in AI-empowered urban ecosystems.
  • Studying the social and economic implications of AI urban deployment, from public trust to job market effects.

5. Scaling from Pilot to Full Implementation

  • Showcasing case studies / pilots where TRL5 research has been deployed in real-world city settings.
  • Examining pathways for larger-scale adoption, including stakeholder engagement, funding models, and policy support.

Suggested or Proposed Lines of Analysis (examples as guidance, not all- inclusive)

1. AI-Augmented Urban Planning and Policy

  • Data-driven frameworks to optimize zoning, resource allocation, 15’ city design and city services.
  • Tools for multi-stakeholder engagement, co-creation, and transparent decision-making processes.

2. Real-Time Monitoring and Predictive Analytics

  • Application of AI algorithms for anomaly detection and rapid response in transit, utilities, and public safety.
  • Integration of IoT sensors with digital twins to manage and forecast urban dynamics.

3. Human-Centric Design and User Experience

  • Methods for engaging citizens and community organizations in AI- enabled projects (e.g., participatory design, processes and tools co-creation, virtual assistants, volunteers’ management).
  • Techniques to enhance trust, transparency, accessibility and inclusivity in AI-based projects.

4. Data Privacy, Security, and Ethical Compliance

  • Approaches to safeguarding personal and infrastructural data, including federated learning or anonymization. Blockchain based identity and digital rights management.
  • Frameworks to ensure responsible AI adoption, including bias mitigation and fairness assessments.

5. Pilot Deployments (TRL5) and Best Practices

  • Empirical results and evaluations from pilot projects, highlighting successes, challenges, and lessons learned.
  • Approaches for long-term maintenance, updates, and scalability of AI-based urban solutions.

We invite contributors to submit high-quality, original research papers detailing minimum validated pilot-level results (TRL5) and offering novel insights into AI applications for city-level transformation. Submissions should describe methodologies, present data-driven findings, and explore practical implications for urban settings.

Deadline: 13 SEPTEMBER 2026

Submissions must be made through the journal's platform. To do so, you must log in or register. Once you have done so, click “Submit an Article” and fill in the required metadata. In the ‘Section’ field, select the option “Special Issue SmartCityExpo”.

For more information on submission guidelines, deadlines, and the review process, please consult the editorial board’s detailed instructions: https://visualcompublications.es/SAUC/about/submissions

We look forward to your contributions shaping the next generation of AI-driven, resilient, and citizen-focused cities.

Keywords
Generative artificial intelligence; Generative spatial artificial intelligence; Urban digital twin; Sustainable smart cities; Agentic AI for Cities; Citizen-centric Urban AI; Social resiliency.

References
Alnaser, A., Maxi, M., & Elmousalami, H. (2024). AI-Powered Digital Twins and Internet of Things for Smart Cities and Sustainable Building Environment. Applied Sciences. https://doi.org/10.3390/app142412056

Chai, H., Wang, H., Li, T., & Wang, Z. (2024). Generative AI-Driven Digital Twin for Mobile Networks. IEEE Network, 38, 84-92. https://doi.org/10.1109/MNET.2024.3420702

Cugurullo, F., & Xu, Y. (2024). When AIs become oracles: generative artificial intelligence, anticipatory urban governance, and the future of cities. Policy and Society. https://doi.org/10.1093/polsoc/puae025

Gkontzis, A., Kotsiantis, S., Feretzakis, G., & Verykios, V. (2024). Enhancing Urban Resilience: Smart City Data Analyses, Forecasts, and Digital Twin Techniques at the Neighborhood Level. Future Internet, 16, 47. https://doi.org/10.3390/fi16020047

Huang, J., Bibri, S., & Keel, P. (2025). Generative Spatial Artificial Intelligence for Sustainable Smart Cities: A Pioneering Large Flow Model for Urban Digital Twin. Environmental Science and Ecotechnology. https://doi.org/10.1016/j.ese.2025.100526

Li, Y. (2025). AI-Enhanced Digital Twins for Energy Efficiency and Carbon Footprint Reduction in Smart City Infrastructure. Applied and Computational Engineering. https://doi.org/10.54254/2755-2721/2025.20569

Li, T., Long, Q., Chai, H., Zhang, S., Jiang, F., Liu, H., Huang, W., Jin, D., & Li, Y. (2025). Generative AI Empowered Network Digital Twins: Architecture, Technologies, and Applications. ACM Computing Surveys. https://doi.org/10.1145/3711682

Tao, Z., Xu, W., Huang, Y., Wang, X., & You, X. (2023). Wireless Network Digital Twin for 6G: Generative AI as a Key Enabler. IEEE Wireless Communications, 31, 2431. https://doi.org/10.1109/MWC.002.2300564

Xu, F., Zhang, J., Gao, C., Feng, J., & Li, Y. (2023). Urban Generative Intelligence (UGI): A Foundational Platform for Agents in Embodied City Environment. ArXiv, abs/2312.11813. https://doi.org/10.48550/arXiv.2312.11813