Harnessing Large Language Models for Disaster Management: A Survey

2025-01-12

AI Summary

Existing research lacks a systematic survey of large language models (LLMs) in end-to-end natural disaster management across preparedness, response, and recovery phases. Method: We propose the first LLM application taxonomy tailored to these three disaster lifecycle stages, integrating disaster management theory with LLM capability mapping. Through bibliometric analysis and multi-case studies, we construct a multidimensional evaluation matrix grounded in 12 publicly available disaster-related corpora (e.g., Hugging Face, NOAA), yielding a structured knowledge base of 87 peer-reviewed studies. Contribution/Results: The study identifies six persistent challenges—including real-time processing, trustworthiness, and low-resource adaptability—and distills four key research directions: interpretability enhancement, cross-phase coordination, domain-aligned fine-tuning, and lightweight deployment. This work fills a critical gap in systematic LLM reviews for disaster science and provides both theoretical foundations and practical guidelines for developing trustworthy, domain-specific LLMs in natural hazard management.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Large language models (LLMs) have revolutionized scientific research with their exceptional capabilities and transformed various fields. Among their practical applications, LLMs have been playing a crucial role in mitigating threats to human life, infrastructure, and the environment. Despite growing research in disaster LLMs, there remains a lack of systematic review and in-depth analysis of LLMs for natural disaster management. To address the gap, this paper presents a comprehensive survey of existing LLMs in natural disaster management, along with a taxonomy that categorizes existing works based on disaster phases and application scenarios. By collecting public datasets and identifying key challenges and opportunities, this study aims to guide the professional community in developing advanced LLMs for disaster management to enhance the resilience against natural disasters.

Problem

• Natural Disaster Management
• Large Language Models
• Challenges and Opportunities

Innovation

• Large Language Models
• Disaster Management
• Natural Disasters