Review article|Harnessing generative AI for enhanced disaster management: A systematic review

A new peer-reviewed article published in Big Earth Data highlights the transformative potential of artificial intelligence (AI) and large language models (LLMs) in disaster management. The study examines how these emerging technologies can enhance preparedness, response, and recovery efforts, potentially mitigating disaster impacts and saving lives.

Citation
Saengtabtim, K., Leelawat, N., Aumnoysombat, R., Adelifar, M., Saengwongwattana, N., Suktavornprasit, G., … Tang, J. (2025). Harnessing generative AI for enhanced disaster management: a systematic review. Big Earth Data, 1–25. https://doi.org/10.1080/20964471.2025.2521157

Abstract

In the consistently evolving artificial intelligence (AI) and large language models (LLMs), many organizations adopt these technologies’ capabilities to solve and assist core operations in many industries. In disaster areas, well-known organizations in disaster management try to shift their focus to apply the potential capabilities of AI and LLM to support disaster management. As AI and LLM continue to develop, this research aims to perform a structured summarization process to identify their current trend that can assist the disaster management process using a systematic review approach. The study follows the guidelines of PRISMA to ensure transparency in the review results. The findings highlighted the outstanding benefits of AI and LLM and the introduction of integrated technologies to facilitate disaster management, which can eventually mitigate disaster impacts and casualties. The refined results also proposed the technologies’ benefits in assisting the decision support process, creating a business continuity plan, and detecting early warnings. However, ethics and transparency remain the main concerns in fully implementing AI and LLM in disaster management operations. Moreover, the SWOT analysis, represented by the TOWS matrix, was also performed to identify core strategies based on internal and external factors for assisting the disaster management operations.

Keywords

Artificial intelligence, disaster management, large language models, systematic review, risk

Big Earth Data is an interdisciplinary Open Access journal which aims to provide an efficient and high-quality platform for promoting the sharing, processing and analyses of Earth-related big data, thereby revolutionizing the cognition of the Earth’s systems. The journal publishes a wide range of content, including Research Articles, Review Articles, Data Notes, Technical Notes, and Perspectives. It is now included in ESCI (IF=3.8, Q1), Scopus (CiteScore=9.0, Q1), Ei Compendex, GEOBASE, and Inspec. Starting from 2023, Big Earth Data has announced a new award series for authors: Best and Outstanding Paper Awards.