Enhancing urban disaster response through AI-driven data visualization for real-time decision support
(This article belongs to the Special Issue Technological Innovations in Emergency Management: Transforming Preparedness, Response, and Recovery)
Abstract
Urban areas face escalating threats from natural disasters due to climate change and rapid urbanization. This research explores how AI-driven data visualization enhances disaster response and supports real-time decision-making processes. The study proposes a reference architecture that integrates multiple data streams with adaptive visualization techniques, an advancement that improves situational awareness and coordination in emergency response environments. The research evaluates the Graph Attention Convolutional U-NET (GAC-UNET) model, which demonstrated high accuracy in flood detection tasks, achieving a 94% dice score and an 89% intersection over union (IoU). Case studies demonstrate practical benefits in real-world disaster situations, which include enhanced disaster impact prediction with greater precision, optimized resource allocation for maximum efficiency, and improved communication among diverse stakeholders in disaster response efforts. The findings reveal that AI-enabled data visualization significantly improves urban disaster response agility and accuracy, ultimately saving lives and reducing economic losses. The proposed framework adds operational capabilities to disaster management and offers improvements over traditional static dashboard systems. However, AI adoption in disaster management faces challenges such as data privacy concerns, security issues, ethical considerations in critical decision-making, and organizational resistance to new technology integration. This research emphasizes human-centered design principles and ethical AI governance frameworks for successful and responsible implementation. Future research should focus on generative AI models for scenario simulation, enhanced real-time predictive analytics capabilities, and community-driven platforms that improve collaboration and accelerate crisis decision-making processes.
Copyright (c) 2025 Author(s)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it for any purpose, even commercially, under the condition that the authors are given credit. With this license, authors hold the copyright.
References
[1]Typhoon Mawar. Available online: https://en.wikipedia.org/w/index.php?title=Typhoon_Mawar&oldid=1286138746 (accessed on 20 March 2025).
[2]Ramírez-Herrera MT, Coca O, Gaidzik K, Vargas Espinosa VH. Hurricane Otis: Category 5 storm effects and cascading hazards in Acapulco Bay, Mexico. Global and Earth Surface Processes Change. 2025; 3: 100004. doi: 10.1016/j.gespch.2025.100004
[3]AI in Disaster Management: Transforming crisis response. Available online: https://ecoskills.academy/ai-in-disaster-managementtransforming-resilience/ (accessed on 20 March 2025).
[4]shywq. Optimizing Disaster Management in Smart Cities with the Urban Metaverse. Available online: https://bizztech.io/disaster-management-with-the-urban-metaverse/ (accessed on 20 March 2025).
[5]Data Driven Disaster Planning in New York, Tokyo, and Taipei. Available online: https://people.climate.columbia.edu/projects/view/2303 (accessed on 2 April 2025).
[6]Mastery T. The Ten Most Important Insights You Need About AI in the Emergency Services Optimization. Available online: https://dotcommagazine.com/2024/12/the-ten-most-important-insights-you-need-about-ai-in-the-emergency-services-optimization/ (accessed on 20 March 2025).
[7]AI In Urban Planning For Disaster Resilience|Restackio. Available online: https://www.restack.io/p/ai-in-urban-planning-answer-disaster-resilience-cat-ai (accessed on 20 March 2025).
[8]AI For Disaster Response Urban Data Analytics|Restackio. Available online: https://www.restack.io/p/ai-for-disaster-response-answer-urban-data-analytics-cat-ai (accessed on 20 March 2025).
[9]How AI And Data Analytics Assist In Emergency Management. Available online: https://fogsolutions.com/faqs-about-ai-artificial-intelligence/how-ai-and-data-analytics-assist-in-emergency-management/ (accessed on 20 March 2025).
[10]Sapra Y. AI in Disaster Management: How Artificial Intelligence is Saving Lives in Emergencies. Available online: https://www.hashstudioz.com/blog/ai-in-disaster-management-how-artificial-intelligence-is-saving-lives-in-emergencies/ (accessed on 20 March 2025).
[11]Kasali K, Oladapo R. Utilizing predictive analytics to improve healthcare access in the United States (U.S.). World Journal of Advanced Research and Reviews. 2025; 25(3): 1465–1470.
[12]Nunavath V, Prinz A. Reference architecture for emergency management operations. In: Proceedings of the 8th IADIS International Conference Information Systems; 4–16 March 2015; Funchal, Portugal.
[13]Danish MU, Buwaneswaran M, Fonseka T, Grolinger K. Graph Attention Convolutional U-NET: A Semantic Segmentation Model for Identifying Flooded Areas. Available online: https://arxiv.org/html/2502.15907v1 (accessed on 20 March 2025).
[14]Khan A, Sohail A, Zahoora U, Qureshi AS. A Survey of the Recent Architectures of Deep Convolutional Neural Networks. Artificial Intelligence Review. 2020; 53(8): 5455–5516. doi: 10.1007/s10462-020-09825-6
[15]AI For Decision Support In Emergency Services|Restackio. Available online: https://www.restack.io/p/ai-for-decision-support-answer-emergency-services-cat-ai (accessed on 20 March 2025).
[16]Revolutionizing Emergency Management: The Role of AI Incident Safety Response Systems–Safetyology.io. Available online: https://safetyology.io/ai-incident-safety-response-systems/ (accessed on 20 March 2025).
[17]The Impact of AI on Emergency Response Systems: Transforming the Way Emergency Services Operate. Available online: https://stepofweb.com/ai-enhanced-emergency-response-systems/ (accessed on 20 March 2025).
[18]Ladris EVAC-1: Powerful Evacuation Model for Disaster Response. Available online: https://www.ladris.com/product/evac-1 (accessed on 20 March 2025).
[19]Leveraging AI for effective emergency management and crisis response. Available online: https://www2.deloitte.com/us/en/insights/industry/public-sector/automation-and-generative-ai-in-government/leveraging-ai-in-emergency-management-and-crisis-response.html (accessed on 20 March 2025).
[20]Bitton M, Haas E, Hirshberg P. How U.S. Cities Are Using AI to Solve Common Problems. Available online: https://www.elizabethedersheim.com/2025/01/10/how-u-s-cities-are-using-ai-to-solve-common-problems/ (accessed on 20 March 2025).
[21]Revolutionizing Emergency Response: How AI is Optimizing Critical Situations–Safetyology.io. Available online: https://safetyology.io/ai-in-emergency-response-optimization/ (accessed on 20 March 2025).
[22]Hagen A, Barr J. Opportunities for Artificial Intelligence in Emergency Management. Available online: https://domesticpreparedness.com/articles/opportunities-for-artificial-intelligence-in-emergency-management (accessed on 20 March 2025).
[23]Shukla A. Beyond Predictions the role of Generative AI in Disaster Response. Available online: https://abhilashshukla.com/tech-and-programming/aiml/beyond-predictions-the-role-of-generative-ai-in-disaster-response/ (accessed on 20 March 2025).
[24]Williams B. Top 10 AI Virtual Agents for Real-Time Data Visualization. Available online: https://insight7.io/top-10-ai-virtual-agents-for-real-time-data-visualization/ (accessed on 21 March 2025).
[25]Rui X, Cao Y, Yuan X, et al. DisasterGAN: Generative Adversarial Networks for Remote Sensing Disaster Image Generation. Remote Sensing. 2021; 13(21): 4284. doi: 10.3390/rs13214284
[26]Ma Z, Mei G, Xu N. Generative deep learning for data generation in natural hazard analysis: Motivations, advances, challenges, and opportunities. Artificial Intelligence Review. 2024; 57(6):1-91. http://dx.doi.org/10.1007/s10462-024-10764-9
[27]Mishra S, Bajpai A, Mohanta A, et al. Dynamic flood risk prediction in Houston: a multi-model machine learning approach. Geocarto International. 2024; 39(1): 2432866. doi: 10.1080/10106049.2024.2432866
[28]Pinto A. Flood Preparedness in Texas with NASA SPoRT’s Streamflow-AI. Available online: https://weather.ndc.nasa.gov/sport/blog/posts/2024/10/20241023_flood_preparedness_in_texas_with_nasa_sports_streamflow-ai/ (accessed on 21 March 2025).
[29]Carlton J. These Smart Cameras Spot Wildfires Before They Spread. Available online: https://www.wsj.com/tech/ai/these-ai-cameras-detect-wildfires-before-they-spread-6b6e3229 (accessed on 20 March 2025).
[30]Li H, Deuser F, Yina W, et al. Cross-View Geolocalization and Disaster Mapping with Street-View and VHR Satellite Imagery: A Case Study of Hurricane IAN. ISPRS Journal of Photogrammetry and Remote Sensing. 2025; 220: 841–854.
[31]Asif A, Khatoon S, Hasan MM, et al. Automatic analysis of social media images to identify disaster type and infer appropriate emergency response. Journal of Big Data. 2021; 8.
[32]Islam MA, Rabbi F, Hossain NUI. Performance evaluation of NLP and CNN models for disaster detection using social media data. Social Network Analysis and Mining. 2024; 14(1): 213. doi: 10.1007/s13278-024-01374-y
[33]Emergency Networking. The Role of Data Analytics in Predicting Emergency Scenarios. Available online: https://www.emergencynetworking.com/post/the-role-of-data-analytics-in-predicting-emergency-scenarios (accessed on 11 April 2025).
[34]Monitor real-time emergencies (Chinese). Available online: https://learn.arcgis.com/en/projects/monitor-real-time-emergencies/ (accessed on 11 April 2025).
[35]Ghafur S, Kristensen S, Honeyford K, et al. A retrospective impact analysis of the WannaCry cyberattack on the NHS. npj Digital Medicine. 2019; 2(1): 1–7. doi: 10.1038/s41746-019-0161-6
[36]DigitalOcean. 10 AI Data Visualization Tools to Present Insights in 2025. Available online: https://www.digitalocean.com/resources/articles/ai-data-visualization-tools (accessed on 20 March 2025).
[37]Unlocking Insights: The Role of AI in Data Visualization. Available online: https://thedatascientist.com/unlocking-insights-the-role-of-ai-in-data-visualization/ (accessed on 20 March 2025).
[38]ESCAP. Leveraging big data and artificial intelligence for sustainable development. Available online: https://www.unescap.org/blog/leveraging-big-data-and-artificial-intelligence-sustainable-development (accessed on 20 March 2025).
[39]AI in Disaster Response and Recovery. Available online: https://blog.weskill.org/2024/12/AI-in-Disaster-Response-and-Recovery.html (accessed on 20 March 2025).
[40]Datafloq. How Cognitive Load Impacts Data Visualization Effectiveness. Available online: https://datafloq.com/read/how-cognitive-load-impacts-data-visualization-effectiveness/ (accessed on 21 March 2025).
[41]Samuel J, Kashyap R, Samuel Y, Pelaez A. Adaptive cognitive fit: Artificial intelligence augmented management of information facets and representations. International Journal of Information Management. 2022; 65: 102505. doi: 10.1016/j.ijinfomgt.2022.102505
[42]Ardianto I. Designing the User Experience o—David Lightbown. Available online: https://www.academia.edu/29001496/Designing_the_User_Experience_o_David_Lightbown (accessed on 21 March 2025).
4.png)
