Agent-Based Modeling and Generative AI for Disaster Response Simulation in Smart Cities
DOI:
https://doi.org/10.63876/ijtm.v5i1.179Keywords:
Agent-Based Modeling, Generative AI, Disaster Response, Smart Cities, Emergency Simulation, Urban ResilienceAbstract
Disaster response in smart cities requires rapid, adaptive, and data-driven decision-making to reduce casualties, infrastructure damage, and service disruption. Urban areas such as Medellín, Colombia, face complex disaster-response challenges due to dense settlements, varied topography, mobility constraints, and exposure to hazards such as floods, landslides, and urban emergencies. This study proposes an integrated agent-based modeling and generative artificial intelligence framework for disaster response simulation in smart cities. The proposed framework models the behavior and interaction of multiple urban agents, including residents, emergency responders, vehicles, hospitals, shelters, transportation networks, and command centers, to simulate disaster scenarios and evaluate response strategies. Agent-based modeling is used to represent individual and institutional decision-making during disaster events, such as evacuation behavior, route selection, emergency dispatch, shelter allocation, and resource distribution. Generative AI is integrated to enhance scenario generation, simulate dynamic emergency narratives, generate synthetic disaster conditions, and support decision-making recommendations under uncertain and rapidly changing environments. The Medellín case context is used to demonstrate how the proposed model can support disaster preparedness, emergency coordination, and smart city resilience planning. The expected results show that combining agent-based modeling with generative AI can improve disaster-response simulation by enabling more flexible scenario exploration, realistic behavioral modeling, and adaptive decision support. This study contributes to the development of intelligent disaster-management systems by bridging simulation modeling, artificial intelligence, and smart city governance. The proposed framework can assist policymakers, urban planners, emergency agencies, and smart city managers in evaluating evacuation plans, optimizing emergency resources, identifying vulnerable areas, and improving disaster-response readiness. Overall, this study highlights the potential of agent-based modeling and generative AI as complementary tools for building more resilient, responsive, and human-centered smart cities.
Downloads
References
[1] N. H. Koroso and J. A. Zevenbergen, “Urban land management under rapid urbanization: Exploring the link between urban land policies and urban land use efficiency in Ethiopia,” Cities, vol. 153, p. 105269, Oct. 2024, doi: https://doi.org/10.1016/j.cities.2024.105269.
[2] M. M. Baig, M. R. Faheem, L. Khan, H. Adeel, and S. A. A. Shah, “Human Behaviour Classification in Emergency Situations Using Machine Learning with Multimodal Data: A Systematic Review (2020–2025),” CMES, vol. 145, no. 3, pp. 2895–2935, 2025, doi: https://doi.org/10.32604/cmes.2025.073172.
[3] D. Lefutso, “Institutional priority lock-in and the limits of disaster response financing: Evidence from South Africa’s 2022 floods,” International Journal of Disaster Risk Reduction, vol. 143, p. 106286, Sep. 2026, doi: https://doi.org/10.1016/j.ijdrr.2026.106286.
[4] F. Long, A. Majumdar, and H. Carter, “Understanding levels of compliance with emergency responder instructions for members of the Public involved in emergencies: Evidence from the Grenfell Tower fire,” International Journal of Disaster Risk Reduction, vol. 84, p. 103374, Jan. 2023, doi: https://doi.org/10.1016/j.ijdrr.2022.103374.
[5] B. Okeowo et al., “Cleaner air, healthier hospitals: Implementing the UK’s Clean Air Hospital Framework,” Journal of Environmental Management, vol. 391, p. 126468, Sep. 2025, doi: https://doi.org/10.1016/j.jenvman.2025.126468.
[6] L. R. Forti, M. R. Pontes, G. Augusto-Alves, A. Martins, F. Hepp, and J. K. Szabo, “Data collected by citizen scientists reveal the role of climate and phylogeny on the frequency of shelter types used by frogs across the Americas,” Zoology, vol. 155, p. 126052, Dec. 2022, doi: https://doi.org/10.1016/j.zool.2022.126052.
[7] J. Gao, A. Pilipchak, X.-Y. Zhou, K. Wang, C. Yu, and W.-L. Shang, “Decarbonizing transportation with intelligent transportation systems: a systematic review of mechanisms, constraints and deployment pathways,” Applied Energy, vol. 425, p. 128493, Dec. 2026, doi: https://doi.org/10.1016/j.apenergy.2026.128493.
[8] S. Zhang, J. Yu, F. Alblehai, A. Tolba, X. Liu, and M. Zhu, “Sustainability assessment of underwater wireless communication networks using fuzzy-TOPSIS for marine environmental protection,” Marine Pollution Bulletin, vol. 231, p. 119992, Oct. 2026, doi: https://doi.org/10.1016/j.marpolbul.2026.119992.
[9] S. Alzebda and M. A. I. Matar, “Factors affecting citizen intention toward AI acceptance and adoption: the moderating role of government regulations,” CR, vol. 35, no. 2, pp. 434–455, Feb. 2025, doi: https://doi.org/10.1108/CR-06-2023-0144.
[10] C. C. Cheang, W.-M. W. So, Y. Zhan, and K. H. Tsoi, “Education for sustainability using a campus eco-garden as a learning environment,” IJSHE, vol. 18, no. 2, pp. 242–262, Feb. 2017, doi: https://doi.org/10.1108/IJSHE-10-2015-0174.
[11] R. J. Marin, M. F. Velásquez, E. F. García, M. Alvioli, and E. Aristizábal, “Assessing two methods of defining rainfall intensity and duration thresholds for shallow landslides in data-scarce catchments of the Colombian Andean Mountains,” CATENA, vol. 206, p. 105563, Nov. 2021, doi: https://doi.org/10.1016/j.catena.2021.105563.
[12] H. Lu et al., “Are industrial areas the main culprit behind urban heat? A study of thermal environment in mountainous cities based on downscaled LST data,” Sustainable Cities and Society, vol. 135, p. 106980, Dec. 2025, doi: https://doi.org/10.1016/j.scs.2025.106980.
[13] C. Ren, S.-M. Hong, and R. Tang, “AgentiControl-MPC: Automated model predictive control for buildings using large language model-based multi-agent system,” Advanced Engineering Informatics, vol. 76, p. 105062, Nov. 2026, doi: https://doi.org/10.1016/j.aei.2026.105062.
[14] M. Novoa-Bravo et al., “Machine learning-based gait classification and genome-wide association identify a QTL for gait type in Colombian paso horses,” iScience, vol. 29, no. 7, p. 116320, Jul. 2026, doi: https://doi.org/10.1016/j.isci.2026.116320.
[15] K. J. Ding, J. M. Gilligan, Y. C. E. Yang, P. Wolski, and G. M. Hornberger, “Assessing food–energy–water resources management strategies at city scale: An agent-based modeling approach for Cape Town, South Africa,” Resources, Conservation and Recycling, vol. 170, p. 105573, Jul. 2021, doi: https://doi.org/10.1016/j.resconrec.2021.105573.
[16] S. Baskutis, V. Gružauskas, P. Leibl, and L. Obcarskas, “Agent-based modelling approach for autonomous vehicle influence on countries’ welfare,” Journal of Cleaner Production, vol. 374, p. 134008, Nov. 2022, doi: https://doi.org/10.1016/j.jclepro.2022.134008.
[17] M. Rashid et al., “Role of Generative Artificial Intelligence in Assisting Systematic Review Process in Health Research: A Systematic Review,” Value in Health, vol. 28, no. 11, pp. 1665–1682, Nov. 2025, doi: https://doi.org/10.1016/j.jval.2025.07.001.
[18] A. Beheshtian, K. P. Donaghy, R. Richard Geddes, and H. Oliver Gao, “Climate-adaptive planning for the long-term resilience of transportation energy infrastructure,” Transportation Research Part E: Logistics and Transportation Review, vol. 113, pp. 99–122, May 2018, doi: https://doi.org/10.1016/j.tre.2018.02.009.
[19] A. S. Ali and S. J. L. Chua, “Factors influencing buyers’ and investors’ decisions in acquiring property in hillside areas,” Ain Shams Engineering Journal, vol. 14, no. 1, p. 101827, Feb. 2023, doi: https://doi.org/10.1016/j.asej.2022.101827.
[20] R. D. Kusumastuti, N. Nurmala, J. Rouli, and L. Trialdi, “Assessing smart city contributions to urban resilience toward disasters,” Progress in Disaster Science, vol. 30, p. 100582, Apr. 2026, doi: https://doi.org/10.1016/j.pdisas.2026.100582.
[21] E. Kirac, D. Shaltayev, and N. Wood, “Evaluating the impact of citizen collaboration with government agencies in disaster response operations: An agent-based simulation study,” International Journal of Disaster Risk Reduction, vol. 106, p. 104469, May 2024, doi: https://doi.org/10.1016/j.ijdrr.2024.104469.
