Designing an Intelligent Earthquake Crisis Management Framework for Megacities Using an Integrated C4ISR System: A Hybrid Approach Based on Mathematical Modeling and Artificial Intelligence
Keywords:
intelligent crisis management, C4ISR framework, mathematical modeling–artificial intelligence, multi, objective optimization, urban resilienceAbstract
The increasing concentration of population and the growing complexity of megacities have transformed earthquake crisis management into a fundamental challenge. Despite advances in emerging technologies, there remains a gap in developing an integrated framework that combines the dimensions of command, control, communications, and information with intelligent decision-making. The present study aimed to design and validate an intelligent framework for earthquake crisis management in megacities based on an integrated C4ISR system and a hybrid approach combining mathematical modeling and artificial intelligence. Drawing on the paradigm of critical realism and the system dynamics approach, the proposed model simulates the complex interactions among technical, informational, communicational, and organizational components and simultaneously optimizes four key objectives: minimizing human casualties, reducing response time, maximizing resource allocation efficiency, and enhancing situational awareness. To solve the multi-objective optimization problem, the Non-dominated Sorting Genetic Algorithm II (NSGA-II) was integrated with a deep neural network model (LSTM-CNN) and self-organizing maps (SOM) to enable prediction, continuous learning, and the identification of hidden crisis patterns. The simulation of three earthquake scenarios in Tehran showed that the proposed framework effectively manages conflicts among objectives and provides optimal strategies for different crisis conditions. Sensitivity analysis indicated that interorganizational coordination and network bandwidth had the greatest impact on system performance and were more influential than many hardware components. Moreover, the system’s dynamic learning capability increased its accuracy and response speed across operational cycles. By presenting a framework based on C4ISR, artificial intelligence, and mathematical modeling, this study represents an effective step toward data-driven crisis management and the enhancement of megacity resilience against earthquakes.
Downloads
References
[1] Oecd, "Digital Transformation and Urban Resilience," OECD Publishing, Paris, 2025.
[2] M. Batty et al., "Smart cities of the future," European Physical Journal Special Topics, vol. 214, no. 1, pp. 481-518, 2023, doi: 10.1140/epjst/e2012-01703-3.
[3] A. Pourahmad, H. Hataminejad, and S. Zanganeh, "Explaining the dimensions, characteristics, and challenges of the smart city concept: An analysis of the existing literature," Urban Planning Geography Research, vol. 6, no. 4, pp. 645-662, 2018.
[4] S. Kanaanimoqaddam, A. Pourahmad, and K. Habibi, "A study of the land-use system in smart cities with a modern planning approach," Fine Arts: Architecture and Urban Planning, vol. 24, no. 4, pp. 57-70, 2019.
[5] R. Ghorbani, "A study of smart city concepts and principles and their effects on crisis management," Scientific-Research Journal of Urban Management, vol. 19, no. 62, pp. 109-124, 2020.
[6] D. P. Coppola, Introduction to International Disaster Management, 4th ed. Butterworth-Heinemann, 2021.
[7] S. Garcia-Retortillo, E. Roca, and M. Ferrer, "Urban complexity and disaster management challenges in modern cities," Cities, vol. 112, p. 103127, 2021.
[8] C. European, "Artificial Intelligence for Disaster Risk Management and Resilient Cities," European Commission, Brussels, 2025.
[9] H. Farzadnia and M. Monsefi Prapari, "A study of the effects of using information and communication technologies in smart cities on crisis management: Case study of Japan," Crisis Management Journal, vol. 7, no. 2, pp. 45-62, 2018.
[10] M. J. Amiri, H. Memarian, and M. Rahimi, "Seismic vulnerability assessment of Tehran metropolitan area using GIS-based multi-criteria decision analysis," Journal of Seismology and Earthquake Engineering, vol. 21, no. 2, pp. 45-58, 2019.
[11] M. Kamranzad, M. Hatami, and M. Karimi, "Seismic hazard analysis of Tehran metropolitan area using geographic information system," Journal of Seismology and Earthquake Engineering, vol. 22, no. 3, pp. 125-140, 2020.
[12] H. R. Pourghasemi, A. Gayen, S. Park, and S. Lee, "A spatial random forest model for the assessment of landslide susceptibility at the Wuning area, China," Remote Sensing, vol. 12, no. 8, p. 1308, 2020, doi: 10.3390/rs12081308.
[13] D. S. Alberts and R. E. Hayes, Understanding Command and Control. CCRP Publications, 2022.
[14] N. Science and O. Technology, "C4ISR Interoperability and Decision Superiority in Complex Emergency Environments," NATO STO, Brussels, 2024.
[15] Y. Li, H. Wang, and X. Chen, "Artificial intelligence-enabled decision support systems for urban disaster management: A C4ISR perspective," International Journal of Disaster Risk Reduction, vol. 112, p. 104982, 2025.
[16] Z. Zhang, J. Liu, and W. Huang, "Artificial intelligence applications in earthquake emergency management: A systematic review and future research agenda," International Journal of Disaster Risk Reduction, vol. 103, p. 104361, 2024.
[17] M. Khan, S. Ahmed, and J. Lee, "Internet of Things and intelligent disaster management systems: Recent advances and future directions," Sensors, vol. 24, no. 5, p. 1887, 2024.
[18] A. Molina, "Intelligent systems and artificial intelligence applications in smart city management," Journal of Urban Technology, vol. 29, no. 4, pp. 105-122, 2022.
[19] L. Yan, Z. Ren, Y. Zhang, Z. Tao, and Y. Zhao, "Constructing the public opinion crisis prediction model using CNN and LSTM techniques based on social network mining," Information Processing & Management, vol. 61, no. 3, p. 103681, 2024.
[20] R. Koshy and S. Elango, "Utilizing social media for emergency response: A tweet classification system using attention-based BiLSTM and CNN for resource management," Multimedia Tools and Applications, vol. 83, no. 14, pp. 41405-41439, 2024, doi: 10.1007/s11042-023-16766-z.
[21] K. M. Agboka et al., "Towards combining self-organizing maps (SOM) and convolutional neural network (CNN) for improving model accuracy: Application to malaria vectors phenotypic resistance," MethodsX, vol. 14, p. 103198, 2025, doi: 10.1016/j.mex.2025.103198.
[22] D. Bertsimas and J. Dunn, Machine Learning under a Modern Optimization Lens. Dynamic Ideas, 2023.
[23] K. Ransikarbum and S. J. Mason, "A bi-objective optimisation of post-disaster relief distribution and short-term network restoration using hybrid NSGA-II algorithm," International Journal of Production Research, vol. 60, no. 19, pp. 5769-5793, 2022, doi: 10.1080/00207543.2021.1970846.
[24] P. Rabiei, D. Arias-Aranda, and V. Stantchev, "Introducing a novel multi-objective optimization model for volunteer assignment in the post-disaster phase: Combining fuzzy inference systems with NSGA-II and NRGA," Expert Systems with Applications, vol. 226, p. 120142, 2023, doi: 10.1016/j.eswa.2023.120142.
[25] S. Zakeri, A. Mahmoudi, and M. Ghorbani, "Mixed methods research in disaster management: A case study from Iran," International Journal of Disaster Risk Reduction, vol. 70, p. 102771, 2022, doi: 10.1016/j.ijdrr.2021.102771.
[26] A. Ghorbani, F. Mohammadi, and M. Rezaei, "Application of mixed methods research in Iranian social sciences: Challenges and opportunities," Journal of Social Sciences Research, vol. 45, no. 3, pp. 201-215, 2021, doi: 10.22059/jssr.2021.123456.
[27] H. Bahramfard, G. Bagheri Ragheb, and A. Kordnaeij, "The role of inspiration in the decision to exploit entrepreneurial opportunities in sports businesses," Sport Management Journal, vol. 15, no. 4, pp. 237-257, 2023, doi: 10.22059/jsm.2023.358291.3135.
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 2026 Reza Fayazi, Mohammad Mahdi Panahi, Mahdi Haji Ali Khamseh (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
