EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physically plausible scenario generation via geo-enhanced LLMs for disaster training

Koki Asami, Kei Hiroi, Michinori Hatayama

Journal of Disaster Science and Management · 08.05.2026 · 2 (1)

DOI: 10.1007/s44367-026-00033-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Disaster Science and Management, online erschienen am 08.05.2026. Verfasst von Koki Asami und 2 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Scenario-based training is central to disaster preparedness, yet creating realistic scenarios is labor-intensive and limited by the weak spatial reasoning of large language models (LLMs). This study introduces a Geo-enhanced prompting framework that integrates elevation, slope, hazard maps, and breach distance into GPT-4.1 prompts to generate physically consistent, time-stepped disaster scenarios. The method was applied to flood response in Hirakata City, Japan, using publicly available geospatial datasets. A total of 740 scenarios were generated across ten locations and 37 timesteps per site, corresponding to realistic training intervals. Evaluation by a municipal crisis-management professional showed that all Geo-enhanced scenarios were physically plausible, while a geography-agnostic baseline produced numerous implausible outputs, including inconsistent inundation sequences. By embedding geospatial constraints directly into prompts, the approach improved temporal coherence and spatial ordering and removed the need for corrections due to physical contradictions. Because the framework relies only on open data and lightweight preprocessing, it is adaptable to other hazards and regions without the cost of model retraining. These findings demonstrate that geospatially grounded LLM prompting can mitigate structural weaknesses in spatial reasoning, offering a scalable pathway to more realistic and operationally useful training materials for disaster preparedness.

Förderung

  • Japan Society for the Promotion of Science

Zitieren

APA

Asami, K., Hiroi, K., & Hatayama, M. (2026). Physically plausible scenario generation via geo-enhanced LLMs for disaster training. Journal of Disaster Science and Management, 2(1). https://doi.org/10.1007/s44367-026-00033-7

Vancouver

Asami K, Hiroi K, Hatayama M. Physically plausible scenario generation via geo-enhanced LLMs for disaster training. Journal of Disaster Science and Management. 2026;2(1). doi:10.1007/s44367-026-00033-7

BibTeX
@article{Asami2026,
  author = {Asami, Koki and Hiroi, Kei and Hatayama, Michinori},
  title = {Physically plausible scenario generation via geo-enhanced LLMs for disaster training},
  journal = {Journal of Disaster Science and Management},
  year = {2026},
  volume = {2},
  number = {1},
  doi = {10.1007/s44367-026-00033-7}
}
Kostenlos starten →