Evolution Toward Cognitive Urban Intelligence: A Systematic Review of Multi-Domain Digital Twins Integrated with Large Language Models

This systematic review has identified the evolution of urban management ranging from monitoring to the dawn of Cognitive Urban Intelligence. By uniting the operational rigor of the "Ingest-to-Actuate" pipeline (Yu et al., 2025) with the semantic depth of Knowledge Graph-driven query systems (Dang et al., 2025), we have identified that the   main challenge facing  current urban intelligence research is the Interdependency Gap. While      the   21 papers reviewed    showing considerable advancement in individual domain such as mobility, flooding and energy it has also identified that current urban intelligence solutions are technology-siloed. This prevent urban resilience from being achieved as there is currently a lack of a unified reasoning engine to handle multi-domain scenarios. This study has identified that the integration of Llama 1.1  and Neo4j can solve this problem as it can unify 20 heterogeneous domains into a single cognitive framework allowing a “What-if reasoning capability that is explainable, proactive, and accessible to non-expert stakeholders.

[1]  S. Z. Ahmad and F. Qamar, "A hybrid AI based framework for enhancing security in satellite based IoT networks using high performance computing architecture," Scientific Reports, vol. 14, no. 1, 2024. [Online].   Available: https://doi.org/10.1038/s41598-024-81234-x [2]  W. Yu et al., "Digital Twin Technology in Smart Cities: A Step Toward Intelligent Urban Management," Energy Reports, vol. 11, pp. 450–465, Dec. 2025. (Base Paper 1) [3]   J. Dang, S. Liu, and C. Wang, "KCitychatBot: A Knowledge Graph-Based Chatbot System for Large-Scale CityGML Urban Models," Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., vol. XLVIII-4/W15-2025,  pp.  99–105,  Sept.  2025. (Base Paper 2) [4]   F. Liu et al., "Hybrid AI-IoT Framework with Digital Twin Integration for Predictive Urban Infrastructure Management in Smart Cities," IEEE Access, vol. 86, no. 1, pp. 1–32, Nov. 2025. [5]  M. Herath et al., "Smart City Digital Edge Core deployment: A Case Study on Traffic and Air Quality Management," in IEEE 11th International Conference on Network Softwarization (NetSoft), July 2025. [6]  A. A. Supianto et al., "An Urban Digital Twin Framework for Reference and Planning," IEEE Access, vol. 12, pp. 152444–152460, Oct. 2024. [7]   "Exploring Digital Twins for Urban Mobility: Applications and Case Study of Helsinki," in 2025 International Workshop on Intelligent Systems (IWIS), Sept. 2025. [Online]. Available: 10.1109/IWIS62632.2025.11142394 [8]     A. B. Pawar et al., "Digital Twin-Based Predictive Analytics for Urban Traffic Optimization and Smart Infrastructure Management," International Journal of Advanced Computer Science and Applications, vol. 16, no. 2, 2025. [9]   D. Chiaro, P. Qi, A. Pescapè, and F. Piccialli, "Generative AI-Empowered Digital Twin: A Comprehensive Survey with Taxonomy," IEEE Transactions on Industrial Informatics, vol. 21, no. 6, June 2025. [10]   C. Ge and S. Qin, "Urban Flooding Digital Twin System Framework: A Lifecycle-Oriented Approach," Systems Science & Control Engineering, vol. 13, no. 1, Jan. 2025.