Volume 9, Issue 4 (12-2025)
EBHPME 2025, 9(4): 0-0 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Marzban A, Emami P. Applications of Artificial Intelligence in Disaster Risk Reduction Management in Flood: A Narrative Review. EBHPME 2025; 9 (4)
URL: http://jebhpme.ssu.ac.ir/article-1-542-en.html
URL: http://jebhpme.ssu.ac.ir/article-1-542-en.html
Department of Emergency Medical Sciences, Faculty of Paramedical Sciences, Kurdistan University of Medical Sciences, Sanandaj, Iran , payamemami115@gmail.com
Abstract: (51 Views)
Background: Floods are among the most frequent and destructive natural disasters globally, exacerbated by climate change, urbanization, and population growth in high-risk areas. The increasing complexity of flood events has intensified the demand for innovative technologies to enhance disaster risk reduction (DRR). This study aims to review the applications of artificial intelligence (AI) in flood-related DRR management.
Methods: A narrative review was conducted following PRISMA guidelines. A comprehensive literature search was performed on July 16, 2025, across Scopus, Web of Science, PubMed, and Google Scholar. Then, keyword combinations targeting AI and flood management were applied to titles, abstracts, and keywords of peer-reviewed articles published between 2015 and 2025. Studies were included if they presented empirical data or technical modeling focused on AI applications in flood risk reduction.
Results: 20 eligible studies revealed diverse AI applications across four key phases: flood prediction, preparedness, emergency response, and post-disaster recovery. Techniques such as machine learning, deep learning, and reinforcement learning improved forecasting accuracy, resource allocation, and damage assessment. However, challenges including data scarcity, model bias, ethical concerns, and limited infrastructure were consistently reported, particularly in vulnerable regions.
Conclusion: AI holds significant promise for enhancing flood DRR, but its implementation requires inclusive design, standardized evaluation frameworks, and stronger community engagement. Future research should prioritize interdisciplinary collaboration to ensure that AI tools are not only technically robust but also socially equitable and contextually relevant.
Methods: A narrative review was conducted following PRISMA guidelines. A comprehensive literature search was performed on July 16, 2025, across Scopus, Web of Science, PubMed, and Google Scholar. Then, keyword combinations targeting AI and flood management were applied to titles, abstracts, and keywords of peer-reviewed articles published between 2015 and 2025. Studies were included if they presented empirical data or technical modeling focused on AI applications in flood risk reduction.
Results: 20 eligible studies revealed diverse AI applications across four key phases: flood prediction, preparedness, emergency response, and post-disaster recovery. Techniques such as machine learning, deep learning, and reinforcement learning improved forecasting accuracy, resource allocation, and damage assessment. However, challenges including data scarcity, model bias, ethical concerns, and limited infrastructure were consistently reported, particularly in vulnerable regions.
Conclusion: AI holds significant promise for enhancing flood DRR, but its implementation requires inclusive design, standardized evaluation frameworks, and stronger community engagement. Future research should prioritize interdisciplinary collaboration to ensure that AI tools are not only technically robust but also socially equitable and contextually relevant.
Type of Study: Review Article |
Subject:
Healt care Management
Received: 2025/07/30 | Accepted: 2025/12/19 | Published: 2025/12/19
Received: 2025/07/30 | Accepted: 2025/12/19 | Published: 2025/12/19
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
