EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Advanced susceptibility analysis of ground deformation disasters using large language models and machine learning: A Hangzhou City case study

Bofan Yu, Huaixue Xing iD, Weiya Ge, Liling Zhou, Jiaxing Yan, Yun-An Li

PLOS ONE · 12.12.2024 · 19 (12) · e0310724

DOI: 10.1371/journal.pone.0310724 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 12.12.2024. Verfasst von Bofan Yu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Nanjing Center, China Geological Survey, Nanjing Center, China Geological Survey, Nanjing, The People's Republic of China. Hauptthemen laut MEDLINE: Machine Learning, Disasters. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the prevailing scenario where comprehensive susceptibility assessments of ground deformation disasters primarily rely on knowledge-driven models, with weight judgments largely founded on expert subjective assessments, this study initially explores the feasibility of integrating data-driven models into the evaluation of urban ground collapse and subsidence. Hangzhou city, characterized by filled soil and silty sand, was selected as the representative study area. Nine pertinent evaluation factors were identified, and the RF-BP neural network coupling model was employed to assess the susceptibility of ground collapse and subsidence in the study area, the results indicate that the stacked model achieved a 7% increase in AUC value compared to the single model. Subsequently, this study utilized the advanced large language model (LLM), ChatGPT-4, to supplant expert judgment in the weight determination of ground deformation disasters. The advantages of ChatGPT-4, such as its ability to process vast amounts of data and provide consistent, unbiased judgments, were highlighted. ChatGPT-4’s assessments were validated by geological experts in the study area through the analytic hierarchy process. The results show that, by analyzing the same textual materials, the weights determined by experts differed by only 3% from those judged by ChatGPT, demonstrating the reliability and human-expert-like logic of ChatGPT-4’s judgments. Finally, a comprehensive susceptibility assessment of ground deformation disasters was conducted utilizing ChatGPT-4’s judgment results, yielding favorable outcomes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningDisastersChinaHumansCitiesNeural Networks, ComputerModels, TheoreticalLanguage

Autor:innen und Institutionen

  • Nanjing Center, China Geological Survey, Nanjing Center, China Geological Survey, Nanjing, The People's Republic of China.
  • The Ministry of Natural Resources' Urban Underground Space Exploration and Evaluation Technology Innovation Center, Qingdao, The People's Republic of China.
  • Zhejiang Institute of Geosciences, Observation and Research Station of Zhejiang Coastal Urban Geological Security, Ministry of Natural Resources, Hangzhou, The People's Republic of China.
  • The Institute of Geological Survey of China University of Geosciences (Wuhan), China University of Geosciences (Wuhan), The People's Republic of China.

ORCID-Profile: Huaixue Xing

Zitieren

APA

Yu, B., Xing, H., Ge, W., Zhou, L., Yan, J., & Li, Y. A. (2024). Advanced susceptibility analysis of ground deformation disasters using large language models and machine learning: A Hangzhou City case study. PLOS ONE, 19(12), e0310724. https://doi.org/10.1371/journal.pone.0310724

Vancouver

Yu B, Xing H, Ge W, Zhou L, Yan J, Li YA. Advanced susceptibility analysis of ground deformation disasters using large language models and machine learning: A Hangzhou City case study. PLOS ONE. 2024;19(12):e0310724. doi:10.1371/journal.pone.0310724

BibTeX
@article{Yu2024,
  author = {Yu, Bofan and Xing, Huaixue and Ge, Weiya and Zhou, Liling and Yan, Jiaxing and Li, Yun-An},
  title = {Advanced susceptibility analysis of ground deformation disasters using large language models and machine learning: A Hangzhou City case study},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {12},
  pages = {e0310724},
  doi = {10.1371/journal.pone.0310724}
}
Kostenlos starten →