EN中文

Journal of Geo-information Science >

2025 , Vol. 27 >Issue 6: 1249 - 1262

DOI: https://doi.org/10.12082/dqxxkx.2025.250175

Typhoon Disaster Knowledge Service Driven by Large Language Models: Key Technologies and Applications

  • HUANG Yi , 1, 2 ,
  • ZHANG Xueying , 3, 4, * ,
  • SHENG Yehua 3, 4 ,
  • XIA Yongqi 1, 2 ,
  • YE Peng 5, 6
Expand
  • 1. School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
  • 2. Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province, Nanjing 210023, China
  • 3. Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023, China
  • 4. Key Laboratory of Virtual Geographic Environment, Nanjing Normal University, Ministry of Education, Nanjing 210023, China
  • 5. Urban Planning and Development Institute, Yangzhou University, Yangzhou 225127, China
  • 6. College of Architectural Science and Engineering, Yangzhou University, Yangzhou 225127, China
*ZHANG Xueying, E-mail:

Received date: 2025-04-17

  Revised date: 2025-05-16

  Online published: 2025-06-05

Supported by

National Natural Science Foundation of China(42401570)

National Natural Science Foundation of China(42471463)

National Key Research and Development Program of China(2021YFB3900903)

Open Foundation of the Key Laboratory of Coupling Process and Effect of Natural Resources Elements(2024KFKT020)

Fold

Abstract

[Objectives] This study addresses the critical challenges in typhoon disaster knowledge services, which are often hindered by "massive data, scarce knowledge, and limited services." The core objective is to rapidly distill actionable knowledge from vast datasets to enhance disaster management efficacy and mitigate typhoon-related impacts. Large Language Models （LLMs）, renowned for their superior performance in natural language processing, are leveraged to deeply mine disaster-related information and provide robust support for advanced knowledge services. [Methods] This research establishes a typhoon disaster knowledge service framework encompassing three layers: data, knowledge, and service. [Results] For the data-to-knowledge layer, an LLM-driven （Qwen2.5-Max） automated method for constructing typhoon disaster Knowledge Graphs （KGs） is proposed. This method first introduces a multi-level typhoon disaster knowledge representation model that integrates spatiotemporal characteristics and disaster impact mechanisms. A specialized training dataset is curated, incorporating typhoon-related texts with explicit temporal and spatial attributes. By adopting a "pre-training + fine-tuning" paradigm, the framework efficiently transforms raw disaster data into structured knowledge. For the knowledge-to-service layer, an LLM-based intelligent question-answering system is developed. Utilizing the constructed typhoon disaster KG, this system employs Graph Retrieval-Augmented Generation （GraphRAG） to retrieve contextually relevant knowledge from the graph and generate user-specific disaster prevention and mitigation guidance. This approach ensures seamless conversion of structured knowledge into practical services, such as personalized evacuation plans and resource allocation strategies. [Conclusions] The study highlights the transformative potential of LLMs in typhoon disaster management and lays a foundation for integrating LLMs with geospatial technologies. This interdisciplinary synergy advances Geographic Artificial Intelligence (GeoAI) and paves the way for innovative applications in disaster service.

Key words： Large Language Models; knowledge service; knowledge graph; Typhoon disaster; intelligent question answering; retrieval-augmented generation; GeoAI

Cite this article

HUANG Yi , ZHANG Xueying , SHENG Yehua , XIA Yongqi , YE Peng . Typhoon Disaster Knowledge Service Driven by Large Language Models: Key Technologies and Applications[J]. Journal of Geo-information Science, 2025 , 27(6) : 1249 -1262 . DOI: 10.12082/dqxxkx.2025.250175

利益冲突：Conflicts of Interest 所有作者声明不存在利益冲突。

All authors disclose no relevant conflicts of interest.

References

Publishing order | Descend order by publishing year | Descend order by cited within
[1]
李泽椿, 张玲, 钱奇峰, 等. 中央气象台台风预报业务的发展及思考[J]. 大气科学学报, 2020, 43(1):10-19.

[Li Z C, Zhang L, Qian Q F, et al. The development and consideration of typhoon forecast operation of National Meteorological Center[J]. Transactions of Atmospheric Sciences, 2020, 43(1):10-19.] DOI:10.13878/j.cnki.dqkxxb.20200110015

[2]
李德仁, 眭海刚, 倪梓轩, 等. 论天空地一体化灾损监测评估[J]. 中国减灾, 2022(5):28-31.

[Li D R, Sui H G, Ni Z X, et al. On disaster monitoring and evaluation of sky-ground integration[J]. Disaster Reduction in China, 2022(5):28-31.] DOI:10.3969/j.issn.1002-4549.2022.05.010

[3]
周成虎, 王华, 王成善, 等. 大数据时代的地学知识图谱研究[J]. 中国科学:地球科学, 2021, 51(7):1070-1079.

[Zhou C H, Wang H, Wang C S, et al. Research on geo-knowledge map in the age of big data[J]. Scientia Sinica (Terrae), 2021, 51(7):1070-1079.] DOI:10.1360/SSTe-2020-0337

[4]
陆锋, 诸云强, 张雪英. 时空知识图谱研究进展与展望[J]. 地球信息科学学报, 2023, 25(6):1091-1105.

DOI

[Lu F, Zhu Y Q, Zhang X Y. Spatiotemporal knowledge graph: Advances and perspectives[J]. Journal of Geo-information Science, 2023, 25(6):1091-1105.] DOI:10.12082/dqxxkx.2023.230154

[5]
张钹, 朱军, 苏航. 迈向第三代人工智能[J]. 中国科学:信息科学, 2020, 50(9):1281-1302.

[Zhang B, Zhu J, Su H. Toward the third generation of artificial intelligence[J]. Scientia Sinica (Informationis), 2020, 50(9):1281-1302.] DOI:10.1360/SSI-2020-0204

[6]
李国杰. 智能化科研(AI4R):第五科研范式[J]. 中国科学院院刊, 2024, 39(1):1-9.

[Li G J. AI4R: The fifth scientific research paradigm[J]. Bulletin of Chinese Academy of Sciences, 2024, 39(1):1-9.] DOI:10.16418/j.issn.1000-30 45.20231007002

[7]
诸云强, 孙凯, 王曙, 等. 顾及复杂时空特征及关系的地球科学知识图谱自适应表达模型[J]. 中国科学:地球科学, 2023, 53(11):2609-2622.

[Zhu Y Q, Sun K, Wang S, et al. An adaptive representation model for geoscience knowledge graphs considering complex spatiotemporal features and relationships.[J] Scientia Sinica (Terrae), 2023, 66(11):2563-2578.] DOI:10.1360/SSTe-2022-0371

[8]
林珲, 游兰, 胡传博, 等. 时空大数据时代的地理知识工程展望[J]. 武汉大学学报(信息科学版), 2018, 43(12):2205-2211.

[Lin H, You L, Hu C B, et al. Prospect of geo-knowledge engineering in the era of spatio-temporal big data[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12):2205-2211.] DOI:10.13203/j.wh ugis20180318

[9]
诸云强, 孙凯, 胡修棉, 等. 大规模地球科学知识图谱构建与共享应用框架研究与实践[J]. 地球信息科学学报, 2023, 25(6):1215-1227.

DOI

[Zhu Y Q, Sun K, Hu X M, et al. Research and practice on the framework for the construction, sharing, and application of large-scale geoscience knowledge graphs[J]. Journal of Geo-information Science, 2023, 25(6):1215-1227.] DOI:10.12082/dqxxkx.2023.210696

[10]
陈军, 刘万增, 武昊, 等. 基础地理知识服务的基本问题与研究方向[J]. 武汉大学学报(信息科学版), 2019, 44(1):38-47.

[Chen J, Liu W Z, Wu H, et al. Basic issues and research agenda of geospatial knowledge service[J]. Geomatics and Information Science of Wuhan University, 2019, 44(1):38-47.] DOI:10.13203/j.whugis20180441

[11]
张雪英, 张春菊, 吴明光, 等. 顾及时空特征的地理知识图谱构建方法[J]. 中国科学:信息科学, 2020, 50(7):1019-1032.

[Zhang X Y, Zhang C J, Wu M G, et al. Spatiotemporal features based geographical knowledge graph construction[J]. Scientia Sinica (Informationis), 2020, 50(7):1019-1032.] DOI:10.1360/SSI-2019-0269

[12]
张永军, 李彦胜, 党博, 等. 多模态遥感基础大模型:研究现状与未来展望[J]. 测绘学报, 2024, 53(10):1942-1954.

[Zhang Y J, Li Y S, Dang B, et al. Multi-modal remote sensing large foundation models: Current research status and future prospect[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(10):1942-1954.] DOI:10.11947/j.AGC S.2024.20240019

[13]
王卷乐, 韩雪华, 卜坤, 等. 防灾减灾知识服务系统及其应用研究[J]. 全球变化数据学报(中英文), 2020, 4(1):16-23.

[Wang J L, Han X H, Bu K, et al. Knowledge service system on disaster risk reduction and its application in social media analysis[J]. Journal of Global Change Data & Discovery, 2020, 4(1):16-23.] DOI:10.3974/geodp.2020.01.03

[14]
Zhang X Y, Huang Y, Zhang C J, et al. Geoscience knowledge graph (GeoKG): Development, construction and challenges[J]. Transactions in GIS, 2022, 26(6):2480-2494. DOI:10.1111/tgis.12985

[15]
侯志伟, 荆文龙, 秦承志, 等. 智能时代的红树林知识服务展望:从植物图谱到知识图谱[J]. 中国科学:地球科学, 2025, 55(1):111-125.

[Hou Z W, Jing W L, Qin C Z, et al. Prospects on mangrove knowledge services in the smart era: From plant atlas to knowledge graphs[J]. Scientia Sinica (Terrae), 2025, 55(1):111-125.] DOI:10.1360/SSTe-2024-0022

[16]
周成虎, 孙九林, 苏奋振, 等. 地理信息科学发展与技术应用[J]. 地理学报, 2020, 75(12):2593-2609.

DOI

[Zhou C H, Sun J L, Su F Z, et al. Geographic information science development and technological application[J]. Acta Geographica Sinica, 2020, 75(12):2593-2609.] DOI:10.11821/dlxb202012004

[17]
Muller E, Zenker A. Business services as actors of knowledge transformation: The role of KIBS in regional and national innovation systems[J]. Research Policy, 2001, 30(9):1501-1516. DOI:10.1016/S0048-7333(01)00164-0

[18]
刘万增, 陈军, 翟曦, 等. 时空知识中心的研究进展与应用[J]. 测绘学报, 2021, 50(9):1183-1193.

DOI

[Liu W Z, Chen J, Zhai X, et al. Research progress and application of spatiotemporal knowledge center[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(9):1183-1193.] DOI:10.11947/j.AGCS.2021.20210160

[19]
王卷乐, 张敏, 袁月蕾, 等. 知识服务驱动“一带一路”防灾减灾[J]. 科技导报, 2020, 38(16):96-104.

DOI

[Wang J L, Zhang M, Yuan Y L, et al. Knowledge services drive disaster risk reduction in the Belt and Road initiative[J]. Science & Technology Review, 2020, 38(16):96-104.] DOI:10.3981/j.issn.1000-7857.2020.16.011

[20]
龚健雅, 耿晶, 吴华意. 地理空间知识服务概论[J]. 武汉大学学报(信息科学版), 2014, 39(8):883-890.

[Gong J Y, Geng J, Wu H Y. Geospatial knowledge service: A review[J]. Geomatics and Information Science of Wuhan University, 2014, 39(8):883-890.] DOI:10.13203/j.whugis20140119

[21]
闵晓冬, 王卷乐, 韩保民, 等. 开放科学背景下全球灾害数据共享平台建设与应用的现状分析[J]. 中国科技资源导刊, 2023, 55(5):41-52,89.

[Min X D, Wang J L, Han B M, et al. Evaluation of the international disaster database under the open science initiative[J]. China Science & Technology Resources Review, 2023, 55(5):41-52,89.] DOI:10.3772/j.issn.1674-1544.2023.05.005

[22]
Hu Y J, Mai G C, Cundy C, et al. Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages[J]. International Journal of Geographical Information Science, 2023, 37(11):2289-2318. DOI:10.1080/13658816.2023.2266495

[23]
Sun H Y, Di Z H, Qin P H, et al. Spatio-temporal variation and dynamic risk assessment of drought and flood disaster (DFD) in China[J]. International Journal of Disaster Risk Reduction, 2024,100:104140. DOI:10.1016/j.ijdrr.2023.104140

[24]
沈伟豪, 钟燕飞, 王俊珏, 等. 多模态数据的洪涝灾害知识图谱构建与应用[J]. 武汉大学学报(信息科学版), 2023, 48(12):2009-2018.

[Shen W H, Zhong Y F, Wang J J, et al. Construction and application of flood disaster knowledge graph based on multi-modal data[J]. Geomatics and Information Science of Wuhan University, 2023, 48(12):2009-2018.] DOI:10.13203/j.whugis20220509

[25]
杨绚, 张立生, 王铸. 基于机器学习算法的县域台风灾害经济损失风险评估[J]. 热带气象学报, 2022, 38(5):651-661.

[Yang X, Zhang L S, Wang Z. Risk assessment for typhoon economic losses in county-based units using machine learning[J]. Journal of Tropical Meteorology, 2022, 38(5):651-661.] DOI:10.16032/j.issn.1004-4965.2022.059

[26]
Schultz M G, Betancourt C, Gong B, et al. Can deep learning beat numerical weather prediction?[J]. Philosophical Transactions of the Royal Society A, 2021, 379(2194):20200097. DOI:10.1098/rsta.2020.0097

[27]
Chang Y P, Wang X, Wang J D, et al. A survey on evaluation of large language models[J]. ACM Transactions on Intelligent Systems and Technology, 2024, 15(3):1-45. DOI:10.1145/3641289

[28]
Raffel C, Shazeer N, Roberts A, et al. Exploring the limits of transfer learning with a unified text-to-text transformer[J]. Journal of machine learning research, 2020, 21(140):1-67.

[29]
Touvron H, Lavril T, Izacard G, et al. LLaMA: Open and efficient foundation language models[EB/OL]. 2023: 2302.13971. https://arxiv.org/abs/2302.13971v1.

[30]
DeepSeek-AI, Guo D Y, Yang D J, et al. DeepSeek-R1:Incentivizing reasoning capability in LLMs via reinforcement learning[EB/OL]. 2025: 2501.12948. https://arxiv.org/abs/2501.12948v

[31]
杨必胜, 陈一平, 邹勤. 从大模型看测绘时空信息智能处理的机遇和挑战[J]. 武汉大学学报(信息科学版), 2023, 48(11):1756-1768.

[Yang B S, Chen Y P, Zou Q. Opportunities and challenges of spatiotemporal information intelligent processing of surveying and mapping in the era of large models[J]. Geomatics and Information Science of Wuhan University, 2023, 48(11):1756-1768.] DOI:10.13203/j.whugis20230378

[32]
王益鹏, 张雪英, 党玉龙, 等. 顾及时空过程的台风灾害事件知识图谱表示方法[J]. 地球信息科学学报, 2023, 25(6):1228-1239.

DOI

[Wang Y P, Zhang X Y, Dang Y L, et al. Knowledge graph representation of typhoon disaster events based on spatiotemporal processes[J]. Journal of Geo-information Science, 2023, 25(6):1228-1239.] DOI:10.12082/dqxxkx.2023.210800

[33]
民政部国家减灾中心. 自然灾害承灾体分类与代码:GB/T 32572-2016[S]. 北京: 中国标准出版社,2016:2-4.

[ National Disaster Reduction Center, Ministry of Civil Affairs. Classification and coding for natural disaster exposure: GB/T 32572-2016[S]. Beijing: Standards Press of China, 2016: 2-4.]

[34]
Tseng Y M, Huang Y C, Hsiao T Y, et al. Two tales of persona in LLMs: A survey of role-playing and personalization[EB/OL]. 2024: 2406.01171. https://arxiv.org/abs/2406.01171v3.

[35]
Wang S, Qiu P Y, Zhu Y Q, et al. Review, framework, and future perspectives of Geographic Knowledge Graph (GeoKG) quality assessment[J]. Geo-spatial Information Science, 2024:1-21. DOI:10.1080/10095020.2024.2403785

[36]
Xue B C, Zou L. Knowledge graph quality management: A comprehensive survey[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(5):4969-4988. DOI:10.1109/TKDE.2022.3150080

[37]
Edge D, Trinh H, Cheng N, et al. From local to global: A graph RAG approach to query-focused summarization[EB/OL]. 2024: 2404.16130. https://arxiv.org/abs/2404.16130v2

[38]
Yang Y, Yih W T, Meek C. WikiQA: A challenge dataset for open-domain question answering[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: ACL, 2015:2013-2018. DOI:10.18653/v1/d15-1237

[39]
Singhal A. Modern information retrieval: A brief overview[J]. IEEE Data Engineering Bulletin, 2001, 24(4):35-43.

[40]
Papineni K, Roukos S, Ward T, et al. BLEU: A method for automatic evaluation of machine translation[C]// Proceedings of the 40th annual meeting of the Association for Computational Linguistics. Philadelphia, 2002:311-318.DOI:10.3115/1073083.1073135

[41]
Ning Y S, Liu H. UrbanKGent: A unified large language model agent framework for urban knowledge graph construction[EB/OL]. 2024: 2402.06861. https://arxiv.org/abs/2402.06861v2

[42]
Wang Q Y, Downey D, Ji H, et al. SciMON: Scientific inspiration machines optimized for novelty[C]//Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers). Stroudsburg, PA, USA: ACL, 2024:279-299. DOI:10.18653/v1/2024.acl-long.18

[43]
Tong S, Mao K, Huang Z, et al. Automating psychological hypothesis generation with AI: When large language models meet causal graph[J]. Humanities and Social Sciences Communications, 2024,11:896. DOI:10.1057/s41599-024-03407-5

[44]
Ma X G. Knowledge graph construction and application in geosciences: A review[J]. Computers & Geosciences, 2022,161:105082. DOI:10.1016/j.cageo.2022.105082

[45]
Zhong L F, Wu J, Li Q, et al. A comprehensive survey on automatic knowledge graph construction[J]. ACM Computing Surveys, 2024, 56(4):1-62. DOI:10.1145/3618295

[46]
Deng C, Zhang T H, He Z M, et al. K2:A foundation language model for geoscience knowledge understanding and utilization[C]// Proceedings of the 17th ACM International Conference on Web Search and Data Mining. ACM, 2024:161-170. DOI:10.1145/3616855.3635772

[47]
Zhang Y F, Wei C, He Z T, et al. GeoGPT: An assistant for understanding and processing geospatial tasks[J]. International Journal of Applied Earth Observation and Geoinformation, 2024,131:103976. DOI:10.1016/j.jag.2024.103976

[48]
张新长, 赵元, 齐霁, 等. 基于AI大模型的文生图技术方法研究及应用[J]. 地球信息科学学报, 2025, 27(1):10-26.

DOI

[Zhang X C, Zhao Y, Qi J, et al. Research and application of text-to-image technology based on AI foundation models[J]. Journal of Geo-information Science, 2025, 27(1):10-26.] DOI:10.12082/dqxxkx.2025.240657

Options
Outlines

/

〈 〉