Automated extraction of spatiotemporal disaster knowledge for urban floods: a multimodal framework based on LLMs and agent
文献类型：期刊论文
| 作者 | Yang, Yichen5,6; Wang, Qiang5,6; Li, Weirong1,7; Wang, Shu2,5,6; Fang, Shifeng5; Sun, Kai3; Wang, Shunli4; Wang, Hao5,6; Dai, Xiaoliang5,6; Li, Zhuan5 |
| 刊名 | INTERNATIONAL JOURNAL OF DIGITAL EARTH
 |
| 出版日期 | 2026-07-01 |
| 卷号 | 19期号:1页码:2640706 |
| 关键词 | Urban floods knowledge extraction spatiotemporal disaster knowledge large language models (LLMs) intelligent agents |
| ISSN号 | 1753-8947 |
| DOI | 10.1080/17538947.2026.2640706 |
| 产权排序 | 1 |
| 文献子类 | Article |
| 英文摘要 | Extracting spatiotemporal disaster knowledge from massive, heterogeneous social media data is crucial for urban flood management but it remains technically challenging. This study proposes a unified framework that integrates Chinese Multimodal Large Language Models with agents to automate cross-modal extraction, using water depth as a representative case. Systematic evaluations against deep learning baselines demonstrate that knowledge-guided prompting enhances geographic extraction precision by 10%-25%. Specifically, DeepSeek R1 and Doubao-1.5-thinking-vision-pro excel in textual and visual tasks, respectively, and they are jointly adopted to maximize overall performance. The framework is applied to urban flood events in China (July-August 2021) to demonstrate practical utility. The framework constructs a structured database containing 96,826 spatiotemporal water depth records by processing 1.53 million texts and 240,000 images. The results successfully capture the evolution of flood events, verifying the robustness of the proposed approach. This study establishes a validated, data-driven approach using agent-based Multimodal Large Language Models, providing essential knowledge infrastructure for post-event analysis and urban flood risk assessment. |
| URL标识 | 查看原文 |
| WOS研究方向 | Physical Geography ; Remote Sensing |
| 语种 | 英语 |
| WOS记录号 | WOS:001710884900001 |
| 出版者 | TAYLOR & FRANCIS LTD |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/221255]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Zhu, Yunqiang |
| 作者单位 | 1.Guangxi Normal Univ, Coll Environm & Resources, Guilin, Peoples R China; 2.Jiangsu Ctr Collaborat Innovat Geog Informat Resou, Nanjing, Peoples R China; 3.Chinese Univ Hong Kong, Dept Geog & Resource Management, Shatin, Hong Kong, Peoples R China; 4.Shenzhen Univ, Sch Architecture & Urban Planning, Shenzhen, Peoples R China 5.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China; 6.Univ Chinese Acad Sci, Beijing, Peoples R China; 7.Guangxi Normal Univ, Guangxi Key Lab Environm Proc & Remediat Ecol Frag, Guilin, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Yang, Yichen,Wang, Qiang,Li, Weirong,et al. Automated extraction of spatiotemporal disaster knowledge for urban floods: a multimodal framework based on LLMs and agent[J]. INTERNATIONAL JOURNAL OF DIGITAL EARTH,2026,19(1):2640706. |
| APA | Yang, Yichen.,Wang, Qiang.,Li, Weirong.,Wang, Shu.,Fang, Shifeng.,...&Zhu, Yunqiang.(2026).Automated extraction of spatiotemporal disaster knowledge for urban floods: a multimodal framework based on LLMs and agent.INTERNATIONAL JOURNAL OF DIGITAL EARTH,19(1),2640706. |
| MLA | Yang, Yichen,et al."Automated extraction of spatiotemporal disaster knowledge for urban floods: a multimodal framework based on LLMs and agent".INTERNATIONAL JOURNAL OF DIGITAL EARTH 19.1(2026):2640706. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。