A GeoAI-Driven and Decision-Oriented Methodology for Multi-Hazard Early Warning System Development

Abstract

Multi‑hazard early warning systems (MHEWS) are widely recognized as one of the most cost‑effective measures for disaster risk reduction and climate adaptation to date. However, intelligent solutions that can dynamically adapt to the heterogeneous disaster risk and impact information requirements of multi‑departmental stakeholders remain scarce. To facilitate a shift from quantity expansion to quality optimization, this study proposed a methodology for MHEWS development from four perspectives: theoretical foundations, operational procedures, algorithmic technologies, and information hubs. The methodology enhances decision support effectiveness through geospatial artificial intelligence (GeoAI). Specifically: (1) Multi‑party collaboration within MHEWS is redefined as GeoAI Agents, enabling customized intelligent services. (2) An evidence‑based early warning decision support mechanism is constructed through the identification of early warning information requirements. (3) Using a multi‑agent deep reinforcement learning algorithm, the system is co‑driven by data and knowledge, adapts to evolving risks, and achieves end‑to‑end integration and training. (4) A geographic knowledge graph is constructed to consolidate and transform multi-dimensional information flows into actionable insights, integrating large language models to enable hybrid reasoning. Together, these methodology components aim to enable the process of spatiotemporal data → risk information → policy knowledge → practical actions. We develop a subdistrict-level prototype (Smart Early Warning Town) as a validation case and conduct empirical evaluation across seven modules. The results assess both the opportunities and barriers of implementing the proposed methodology and outline an initial pathway for leveraging intelligent approaches to bridge the gap between global high-level visions and routine operational practice.

Keywords

Decision support / Disaster risk scenarios / GeoAI / GeoKG / MA-DRL / Multi-hazard early warning

References

[1] Aguirre-Ayerbe, I., M. Merino, S.L. Aye, R. Dissanayake, F. Shadiya, and C.M. Lopez. 2020. An evaluation of availability and adequacy of multi-hazard early warning systems in Asian countries: A baseline study. International Journal of Disaster Risk Reduction 49: Article 101749.

[2] Akhyar, A., M.A. Zulkifley, J. Lee, T. Song, J. Han, C. Cho, S. Hyun, Y. Son, et al. 2024. Deep artificial intelligence applications for natural disaster management systems: A methodological review. Ecological Indicators 163: Article 112067.

[3] Albahri, A.S., Y.L. Khaleel, M.A. Habeeb, R.D. Ismael, Q.A. Hameed, M. Deveci, R.Z. Homod, O.S. Albahri, et al. 2024. A systematic review of trustworthy artificial intelligence applications in natural disasters. Computers and Electrical Engineering 118: Article 109409.

[4] Alcántara-Ayala I, Oliver-Smith A. Early warning systems: Lost in translation or late by definition? A FORIN approach. International Journal of Disaster Risk Science, 2019, 10(3): 317-331

[5] Attoh, E.M.N.A.N., and G. Amarnath. 2025. A framework for addressing the interconnectedness of early warning to action and finance to strengthen multiscale institutional responses to climate shocks and disasters. Climate Risk Management 47: Article 100689.

[6] Ba R, Deng Q, Liu Y, Yang R, Zhang H. Multi-hazard disaster scenario method and emergency management for urban resilience by integrating experiment-simulation-field data. Journal of Safety Science and Resilience, 2021, 2(2): 77-89

[7] Budimir, M., R.Š. Trogrlić, C. Almeida, M. Arestegui, O.C. Vásquez, A. Cisneros, M.C. Iriarte, A. Dia, et al. 2025. Opportunities and challenges for people-centered multi-hazard early warning systems: Perspectives from the Global South. iScience 28(5): Article 112353.

[8] Cao, Y., L. Deng, X. Liu, Z. Feng, and Y. Gao. 2025. Ethical challenges in the algorithmic era: A systematic rapid review of risk insights and governance pathways for nursing predictive analytics and early warning systems. BMC Medical Ethics 26(1): Article 151.

[9] De Elía R, Ruiz JJ, Francce V, Lohigorry P, Saucedo M, Menalled M, D’Amen D. Early warning systems and end-user decision-making: A risk formalism tool to aid communication and understanding. Risk Analysis, 2024, 44(5): 1128-1142

[10] Demertzis K, Iliadis L, Pimenidis E. Geo-AI to aid disaster response by memory-augmented deep reservoir computing. Integrated Computer-Aided Engineering, 2021, 28(4): 383-398

[11] Dumitrescu, C., V. Radu, R. Gheorghe, A.I. Tăbîrcă, M.C. Ștefan, and L. Manea. 2024. Crowd panic behavior simulation using multi-agent modeling. Electronics 13(18): Article 3622.

[12] El Morr C, Ozdemir D, Asdaah Y, Saab A, El-Lahib Y, Sokhn ES. AI-based epidemic and pandemic early warning systems: A systematic scoping review. Health Informatics Journal, 2024, 30(3): 1-38

[13] Gao S, Hu Y, Li W. Handbook of geospatial artificial intelligence, 2023, Boca Raton. CRC Press

[14] Garcia C, Fearnley CJ. Evaluating critical links in early warning systems for natural hazards. Environmental Hazards, 2012, 11(2): 123-137

[15] Ge, X., Y. Yang, J. Chen, W. Li, Z. Huang, W. Zhang, and L. Peng. 2022. Disaster prediction knowledge graph based on multi-source spatio-temporal information. Remote Sensing 14(5): Article 1214.

[16] Gevaert, C.M., M. Carman, B. Rosman, Y. Georgiadou, and R. Soden. 2021. Fairness and accountability of AI in disaster risk management: Opportunities and challenges. Patterns 2(11): Article 100363.

[17] Ghaffarian, S., F.R. Taghikhah, and H.R. Maier. 2023. Explainable artificial intelligence in disaster risk management: Achievements and prospective futures. International Journal of Disaster Risk Reduction 98: Article 104123.

[18] Hamid H, Abedlmajid E. Intelligent agents in disaster risk management: A systematic review of advances and challenges. International Journal of Advanced Computer Science and Applications, 2025, 16(6): 1019-1029

[19] Haque, A., Shampa, M. Akter, M. Hussain, R. Rahman, M. Salehin, and M. Rahman. 2024. An integrated risk-based early warning system to increase community resilience against disaster. Progress in Disaster Science 21: Article 100310.

[20] He, Y., Y. Huang, Y. Sheng, X. Su, S. Zhou, S. Lei, X. Wang, Y. Xia, et al. 2025. SceneKG: A geo-scene based spatiotemporal knowledge representation framework considering geo-processes. Transactions in GIS 29(1): Article e13270.

[21] Hermans TDG, Šakić Trogrlić R, van den Homberg MJC, Bailon H, Sarku R, Mosurska A. Exploring the integration of local and scientific knowledge in early warning systems for disaster risk reduction: A review. Natural Hazards, 2022, 114(2): 1125-1152

[22] Hofmeister, M., G. Brownbridge, M. Hillman, S. Mosbach, J. Akroyd, K.F. Lee, and M. Kraft. 2024. Cross-domain flood risk assessment for smart cities using dynamic knowledge graphs. Sustainable Cities and Society 101: Article 105113.

[23] IPCC (Intergovernmental Panel on Climate Change). 2023. AR6 synthesis report: Climate change 2023. Geneva: IPCC. https://www.ipcc.ch/report/ar6/syr/. Accessed 8 Dec 2025.

[24] ITU (International Telecommunication Union). 2024. Global initiative on resilience to natural hazards through AI solutions. Geneva: ITU. https://www.itu.int/en/ITU-T/extcoop/ai4resilience/Pages/default.aspx. Accessed 17 Dec 2025.

[25] Jayasekara, R., C. Siriwardana, D. Amaratunga, and R. Haigh. 2022. Evaluating the network of stakeholders in multi-hazard early warning systems for multiple hazards amidst biological outbreaks: Sri Lanka as a case in point. Progress in Disaster Science 14: Article 100228.

[26] Kelman, I., and C.J. Fearnley. 2025. From multi-hazard early warning systems (MHEWS) to all-vulnerability warning systems (AVWS). iScience 28(7): Article 112977.

[27] Keykhaei, M., N.N. Samany, M. Jelokhani-Niaraki, and S. Zlatanova. 2024. Multi-agent-based human cognition simulation of situation-aware earthquake emergency evacuation. International Journal of Disaster Risk Reduction 100: Article 104183.

[28] Khan AR, Rouf A, Sultana N, Akter S. Development of a fog computing-based real-time flood prediction and early warning system using machine learning and remote sensing data. Journal of Sustainable Development and Policy, 2025, 1(1): 144-169

[29] Koldasbayeva, D., P. Tregubova, M. Gasanov, A. Zaytsev, A. Petrovskaia, and E. Burnaev. 2024. Challenges in data-driven geospatial modeling for environmental research and practice. Nature Communications 15(1): Article 10700.

[30] Lavrinovics, E., R. Biswas, J. Bjerva, and K. Hose. 2025. Knowledge graphs, large language models, and hallucinations: An NLP perspective. Journal of Web Semantics 85: Article 100844.

[31] Lee HR, Lee T. Multi-agent reinforcement learning algorithm to solve a partially-observable multi-agent problem in disaster response. European Journal of Operational Research, 2021, 291(1): 296-308

[32] Li X, Zheng D, Feng M, Chen F. Information geography: The information revolution reshapes geography. Science China Earth Sciences, 2022, 65(2): 379-382

[33] Li, B., P. Qi, B. Liu, S. Di, J. Liu, J. Pei, J. Yi, and B. Zhou. 2023. Trustworthy AI: From principles to practices. ACM Computing Surveys 55(9): Article 177.

[34] Li, H., P. Yue, H. Wu, B. Teng, Y. Zhao, and C. Liu. 2025. A question-answering framework for geospatial data retrieval enhanced by a knowledge graph and large language models. International Journal of Digital Earth 18(1): Article 2510566.

[35] Liang J, Hou S, Zhao A, Xu Q, Xiang L, Li R, Wu H. Design and application of a semantic-driven geospatial modeling knowledge graph based on large language models. Geo-spatial Information Science, 2025,

[36] Liang, L., Z. Bo, Z. Gui, Z. Zhu, L. Zhong, P. Zhao, M. Sun, Z. Zhang, et al. 2025. KAG: Boosting LLMs in professional domains via knowledge augmented generation. In Companion Proceedings of the ACM on Web Conference 2025, 28 April–2 May 2025, Sydney, NSW, Australia, 334–343.

[37] Lopez, A., E. Coughlan de Perez, J. Bazo, P. Suarez, B. van den Hurk, and M. van Aalst. 2020. Bridging forecast verification and humanitarian decisions: A valuation approach for setting up action-oriented early warnings. Weather and Climate Extremes 27: Article 100167.

[38] Lü G, Yuan L, Yu Z. Information geography: A new fulcrum of geographic ternary world. Science China Earth Sciences, 2022, 65(2): 383-386

[39] Mai G, Huang W, Sun J, Song S, Mishra D, Liu N, Gao S, Liu T. On the opportunities and challenges of foundation models for GeoAI (vision paper). ACM Transactions on Spatial Algorithms and Systems, 2024, 10(2): 1-46

[40] Mai, G., Y. Xie, X. Jia, N. Lao, J. Rao, Q. Zhu, Z. Liu, Y.Y. Chiang, et al. 2025. Towards the next generation of geospatial artificial intelligence. International Journal of Applied Earth Observation and Geoinformation 136: Article 104368.

[41] Marchezini V, Trajber R, Olivato D, Munoz VA, de Oliveira Pereira F, Oliveira Luz AE. Participatory early warning systems: Youth, citizen science, and intergenerational dialogues on disaster risk reduction in Brazil. International Journal of Disaster Risk Science, 2017, 8(4): 390-401

[42] Merz, B., C. Kuhlicke, M. Kunz, M. Pittore, A. Babeyko, D.N. Bresch, D.I.V. Domeisen, F. Feser, et al. 2020. Impact forecasting to support emergency management of natural hazards. Reviews of Geophysics 58(4): Article e2020RG000704.

[43] Mortaheb R, Jankowski P. Smart city re-imagined: City planning and GeoAI in the age of big data. Journal of Urban Management, 2023, 12(1): 4-15

[44] Najafi, H., P.K. Shrestha, O. Rakovec, H. Apel, S. Vorogushyn, R. Kumar, S. Thober, B. Merz, et al. 2024. High-resolution impact-based early warning system for riverine flooding. Nature Communications 15(1): Article 3726.

[45] Nájera, J.Z., C.C. Luna, and J.J.V. Upegui. 2024. Performance assessment of indicators of a multi-hazards early warning system in an urban mountain region. International Journal of Disaster Risk Reduction 112: Article 104767.

[46] Nearing G, Cohen D, Dube V, Gauch M, Gilon O, Harrigan S, Hassidim A, Klotz D, et al. . Global prediction of extreme floods in ungauged watersheds. Nature, 2024, 627(8004): 559-563

[47] Ou, T.H., T.H. Yang, and P.Z. Chang. 2025. Combination of large language models and portable flood sensors for community flood response: A preliminary study. Water 17(7): Article 1055.

[48] Oyebode O. Explainable deep learning integrated with decentralized identity systems to combat bias, enhance trust, and ensure fairness in algorithmic governance. World Journal of Advanced Research and Reviews, 2024, 21(2): 2146-2166

[49] Painter, P., K. Semmens, K. Maxfield, C. Cattoën, and R.H. Carr. 2025. Designing effective flood early warning systems: A review of barriers, best practices, and key characteristics. Journal of Flood Risk Management 18(4): Article e70145.

[50] Pescaroli, G., S. Dryhurst, and G.M. Karagiannis. 2025. Bridging gaps in research and practice for early warning systems: New datasets for public response. Frontiers in Communication 10: Article 1451800.

[51] Qu, X., C. Wang, R. Zhao, M. Fang, and X. Xie. 2025. Multi-source data-driven Bayesian network for risk analysis of maritime accidents in the high sea. Frontiers in Marine Science 12: Article 1631650.

[52] Reichstein, M., V. Benson, J. Blunk, G. Camps-Valls, F. Creutzig, C. Fearnley, B. Han, K. Kornhuber, et al. 2025. Early warning of complex climate risk with integrated artificial intelligence. Nature Communications 16(1): Article 2564.

[53] Rezvani, S.M.H.S., A. Gonçalves, M.J.F. Silva, and N.M. de Almeida. 2024. Smart hotspot detection using geospatial artificial intelligence: A machine learning approach to reduce flood risk. Sustainable Cities and Society 115: Article 105873.

[54] Rogers DP, Anderson-Berry L, Bogdanova A-M, Fleming G, Gitay H, Kahandawa S, Kootval H, Staudinger M, et al. . Learning from multi-hazard early warning systems to respond to pandemics, 2020, Washington, DC. World Bank Group

[55] Rokhideh M, Fearnley C, Budimir M. Multi-hazard early warning systems in the Sendai Framework for Disaster Risk Reduction: Achievements, gaps, and future directions. International Journal of Disaster Risk Science, 2025, 16(1): 103-116

[56] Saunders, K.R., O. Forbes, J.K. Hopf, C.R. Patterson, S.A. Vollert, K. Brown, R. Browning, M.A. Canizares, et al. 2025. Data-driven recommendations for enhancing real-time natural hazard warnings. One Earth 8(5): Article 101274.

[57] Shi M, Janowicz K, Verstegen J, Currier K, Wiedemann N, Mai G, Majic I, Liu Z, et al. . Geography for AI sustainability and sustainability for GeoAI. Cartography and Geographic Information Science, 2025, 52(4): 331-349

[58] Tiggeloven, T., S. Pfeiffer, A. Matanó, M. Van Den Homberg, L. Thalheimer, M. Reichstein, and S. Torresan. 2025. The role of artificial intelligence for early warning systems: Status, applicability, guardrails, and ways forward. iScience 28(11): Article 113689.

[59] Tupper AC, Fearnley CJ. Disaster early-warning systems are “doomed to fail”—only collective action can plug the gaps. Nature, 2023, 623(7987): 478-482

[60] UNDP (United Nations Development Programme). 2025. What are early warning systems and why do they matter for climate action?https://climatepromise.undp.org/news-and-stories/what-are-early-warning-systems-and-why-do-they-matter-climate-action. Accessed 11 Dec 2025.

[61] UNDRR (United Nations Office for Disaster Risk Reduction) and WMO (World Meteorological Organization). 2025. Global status of multi-hazard early warning systems 2025. Geneva: UNDRR. https://www.undrr.org/reports/global-status-mhews-2025. Accessed 13 Dec 2025.

[62] UNISDR (United Nations International Strategy for Disaster Reduction). 2015. Sendai framework for disaster risk reduction 2015–2030. Geneva: UNISDR. https://www.unisdr.org/files/43291_sendaifra-meworkford-rren.pdf. Accessed 8 Dec 2025.

[63] Velazquez, O., G. Pescaroli, G. Cremen, and C. Galasso. 2020. A review of the technical and socio-organizational components of earthquake early warning systems. Frontiers in Earth Science 8: Article 533498.

[64] WMO (World Meteorological Organization). 2022. Executive action plan 2023–2027. Geneva: WMO. https://library.wmo.int/idurl/4/58209. Accessed 8 Dec 2025.

[65] Wu, R., M. Huang, H. Ma, J. Huang, Z. Li, H. Mei, and C. Wang. 2025. A multi-temporal knowledge graph framework for landslide monitoring and hazard assessment. GeoHazards 6(3): Article 39.

[66] Xu, Q., Y. Shi, J.L. Bamber, C. Ouyang, and X.X. Zhu. 2024. Large-scale flood modeling and forecasting with FloodCast. Water Research 264: Article 122162.

[67] Yu, Z., J. Jiang, B. He, M. Bilal, and D. Liu. 2023. Edge intelligence-driven meteorological knowledge graph for real-time decision-making. In Proceedings of the 2023 IEEE 29th International Conference on Parallel and Distributed Systems (ICPADS), 17–21 December 2023, Ocean Flower Island, China, 2663–2672.

[68] Zhang, J., X. Ruan, H. Si, and X. Wang. 2025. Dynamic hazard analysis on construction sites using knowledge graphs integrated with real-time information. Automation in Construction 170: Article 105938.

[69] Zhang, J., J. Zhu, Z. Guo, J. Wu, Y. Guo, J. Lai, and W. Li. 2025. More intelligent knowledge graph: A large language model-driven method for knowledge representation in geospatial digital twins. International Journal of Applied Earth Observation and Geoinformation 139: Article 104527.

[70] Zou, X., Y. Yan, X. Hao, Y. Hu, H. Wen, E. Liu, J. Zhang, Y. Li, et al. 2025. Deep learning for cross-domain data fusion in urban computing: Taxonomy, advances, and outlook. Information Fusion 113: Article 102606.

RIGHTS & PERMISSIONS

The Author(s)