single-dr.php

JDR Vol.20 No.3 pp. 386-395
(2025)
doi: 10.20965/jdr.2025.p0386

Paper:

Autonomous Epidemic and Geographic Disaster Mapping: Assessing the Performance of Large Language Models in Spatial Information Integration

Wan-Chih Lin* and Ming-Hseng Tseng*,**,† ORCID Icon

*Department of Medical Informatics, Chung Shan Medical University
No.110, Section 1, Jianguo North Road, Taichung 40211, Taiwan

**Information Technology Office, Chung Shan Medical University Hospital
Taichung, Taiwan

Corresponding author

Received:
October 17, 2024
Accepted:
March 16, 2025
Published:
June 1, 2025
Keywords:
disaster, autonomous map generation, LLM, dengue fever, earthquake disaster
Abstract

This study aims to evaluate the performance of various large language models (LLMs) in generating dengue fever epidemic and earthquake intensity maps through the integration of spatial information technology. By combining natural language processing techniques, this paper presents an innovative method to extract real-time data related to dengue fever and earthquake events, which is then used to generate corresponding geographic information maps, thereby improving real-time monitoring and disaster management efficiency. The research designed a series of detailed prompts, including topic descriptions, data sources, analysis objectives, and specific requirements, to test the capabilities of multiple LLMs in the code generation process. The codes generated by these models were further used to map the geographic distribution of dengue fever outbreaks and earthquake intensities in Taiwan. Subsequently, the codes were evaluated on accuracy, operational efficiency, and the clarity of the visualized results. The findings revealed that in addition to ChatGPT, models such as Copilot, Claude, and Nxcode-CQ-7B-orpo also excelled at generating precise and efficient maps. These LLMs are capable of automating the processing of large amounts of data and generating visualized charts with decision support functions, significantly reducing the time and labor costs associated with traditional manual operations. In addition, this innovative approach provides a new technical pathway for real-time geographic disaster monitoring and management. The results underscore the value of integrating LLMs with spatial information technology, offering new research directions for geographic information systems applications and providing robust technical support for disaster response and public health management.

Cite this article as:
W. Lin and M. Tseng, “Autonomous Epidemic and Geographic Disaster Mapping: Assessing the Performance of Large Language Models in Spatial Information Integration,” J. Disaster Res., Vol.20 No.3, pp. 386-395, 2025.
Data files:
References
  1. [1] P.-C. Wu et al., “Higher temperature and urbanization affect the spatial patterns of dengue fever transmission in subtropical Taiwan,” Science of the Total Environment, Vol.407, No.7, pp. 2224-2233, 2009. https://doi.org/10.1016/j.scitotenv.2008.11.034
  2. [2] S. J. Connor et al., “Environmental information systems in malaria risk mapping and epidemic forecasting,” Disasters, Vol.22, No.1, pp. 39-56, 1998. https://doi.org/10.1111/1467-7717.00074
  3. [3] L. Wang et al., “A survey on large language model based autonomous agents,” Frontiers of Computer Science, Vol.18, No.6, Article No.186345, 2024. https://doi.org/10.1007/s11704-024-40231-1
  4. [4] A. Radford et al., “Language models are unsupervised multitask learners,” OpenAI blog, Vol.1, No.8, Article No.9, 2019.
  5. [5] T. B. Brown et al., “Language models are few-shot learners,” Proc. of the 34th Int. Conf. on Neural Information Processing Systems, pp. 1877-1901, 2020.
  6. [6] H. Touvron et al., “LLaMa: Open and efficient foundation language models,” arXiv:2302.13971, 2023. https://doi.org/10.48550/arXiv.2302.13971
  7. [7] H. Touvron et al., “Llama 2: Open foundation and fine-tuned chat models,” arXiv:2307.09288, 2023. https://doi.org/10.48550/arXiv.2307.09288
  8. [8] Anthropic, “Model Card and Evaluations for Claude Models,” 2023. https://www-cdn.anthropic.com/bd2a28d2535bfb0494cc8e2a3bf135d2e7523226/Model-Card-Claude-2.pdf [Accessed October 17, 2024]
  9. [9] J. Achiam et al., “GPT-4 technical report,” arXiv:2303.08774, 2023. https://doi.org/10.48550/arXiv.2303.08774
  10. [10] P. Vaithilingam, T. Zhang, and E. L. Glassman, “Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models,” CHI. Conf. on Human Factors in Computing Systems Extended Abstracts, Article No.332, 2022. https://doi.org/10.1145/3491101.3519665
  11. [11] Z. Li and H. Ning, “Autonomous GIS: The next-generation AI-powered GIS,” Int. J. of Digital Earth, Vol.16, No.2, pp. 4668-4686, 2023. https://doi.org/10.1080/17538947.2023.2278895
  12. [12] “Folium: Python data, leaflet.js maps,” 2024. https://python-visualization.github.io/folium [Accessed October 17, 2024]
  13. [13] W. McKinney, “pandas: A foundational Python library for data analysis and statistics,” Python for High Performance and Scientific Computing, Vol.14, No.9, pp. 1-9, 2011.
  14. [14] “JSON encoder and decoder,” 2024. https://docs.python.org/3/library/json.html [Accessed October 17, 2024]
  15. [15] OpenAI, “ChatGPT,” 2024. https://openai.com/chatgpt/ [Accessed October 17, 2024]
  16. [16] Microsoft, “Copilot,” 2024. https://www.bing.com/chat [Accessed October 17, 2024]
  17. [17] Anthropic, “Claude,” 2024. https://claude.ai [Accessed October 17, 2024]
  18. [18] M. Wrigley, “Chatbot UI,” 2024. https://www.chatbotui.com [Accessed October 17, 2024]
  19. [19] L. Labs, “Code LATS,” 2024. https://huggingface.co/spaces/lapisrocks/CodeLATS [Accessed October 17, 2024]
  20. [20] Meta, “Code Llama,” 2023. https://codellama.dev [Accessed October 17, 2024]
  21. [21] Y. Lin, “Taiwan LLM,” 2024. https://twllm.com [Accessed October 17, 2024]
  22. [22] Google, “Gemini,” 2024. https://gemini.google.com [Accessed October 17, 2024]
  23. [23] H. F. ServiceNow, “BigCode,” 2024. https://huggingface.co/bigcode [Accessed October 17, 2024]
  24. [24] Bartowski, “Nxcode-CQ-7B-orpo,” 2024. https://huggingface.co/bartowski/Nxcode-CQ-7B-orpo-GGUF [Accessed October 17, 2024]
  25. [25] Mistral AI, “Codestral-22B-v0.1,” 2024. https://huggingface.co/mistralai/Codestral-22B-v0.1 [Accessed October 17, 2024]
  26. [26] Qwen, “CodeQwen1.5-7B-Chat,” 2024. https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat [Accessed October 17, 2024]
  27. [27] Mistral AI, “Mixtral-8x7B-Instruct,” 2024. https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1 [Accessed October 17, 2024]
  28. [28] Projection, Mistral AI, “OpenCodeInterpreter-DS-33B,” 2024. https://huggingface.co/m-a-p/OpenCodeInterpreter-DS-33B [Accessed October 17, 2024]
  29. [29] Mistral AI, “Mistral-7B-Instruct,” 2024. https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1 [Accessed October 17, 2024]
  30. [30] C. AI, “CodeFuse-CodeLlama-34b,” 2024. https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B [Accessed October 17, 2024]
  31. [31] Deepseek, “Deepseek-Coder-7B-Instruct,” 2024. https://huggingface.co/deepseek-ai/deepseek-coder-7B-Instruct-v1.5 [Accessed October 17, 2024]

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on May. 31, 2025