EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

WaterGPT: Training a Large Language Model to Become a Hydrology Expert

Yi Ren, Tianyi Zhang, Xurong Dong, Weibin Li, Zhiyang Wang, Jie He, Hanzhi Zhang, Licheng Jiao

Water · 27.10.2024 · 16 (21) · 3075

DOI: 10.3390/w16213075 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water, online erschienen am 27.10.2024. Verfasst von Yi Ren und 7 weiteren Autor:innen. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, the research project of Shaanxi Coal Geology Group Co., Ltd., Shaanxi Provincial Water Conservancy Fund Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper introduces WaterGPT, a language model designed for complex multimodal tasks in hydrology. WaterGPT is applied in three main areas: (1) processing and analyzing data such as images and text in water resources, (2) supporting intelligent decision-making for hydrological tasks, and (3) enabling interdisciplinary information integration and knowledge-based Q&A. The model has achieved promising results. One core aspect of WaterGPT involves the meticulous segmentation of training data for the supervised fine-tuning phase, sourced from real-world data and annotated with high quality using both manual methods and GPT-series model annotations. These data are carefully categorized into four types: knowledge-based, task-oriented, negative samples, and multi-turn dialogues. Additionally, another key component is the development of a multi-agent framework called Water_Agent, which enables WaterGPT to intelligently invoke various tools to solve complex tasks in the field of water resources. This framework handles multimodal data, including text and images, allowing for deep understanding and analysis of complex hydrological environments. Based on this framework, WaterGPT has achieved over a 90% success rate in tasks such as object detection and waterbody extraction. For the waterbody extraction task, using Dice and mIoU metrics, WaterGPT’s performance on high-resolution images from 2013 to 2022 has remained stable, with accuracy exceeding 90%. Moreover, we have constructed a high-quality water resources evaluation dataset, EvalWater, which covers 21 categories and approximately 10,000 questions. Using this dataset, WaterGPT achieved the highest accuracy to date in the field of water resources, reaching 83.09%, which is about 17.83 points higher than GPT-4.

Förderung

  • National Natural Science Foundation of China
  • the research project of Shaanxi Coal Geology Group Co., Ltd.
  • Shaanxi Provincial Water Conservancy Fund Project

Zitieren

APA

Ren, Y., Zhang, T., Dong, X., Li, W., Wang, Z., He, J., Zhang, H., & Jiao, L. (2024). WaterGPT: Training a Large Language Model to Become a Hydrology Expert. Water, 16(21), 3075. https://doi.org/10.3390/w16213075

Vancouver

Ren Y, Zhang T, Dong X, Li W, Wang Z, He J, et al. WaterGPT: Training a Large Language Model to Become a Hydrology Expert. Water. 2024;16(21):3075. doi:10.3390/w16213075

BibTeX
@article{Ren2024,
  author = {Ren, Yi and Zhang, Tianyi and Dong, Xurong and Li, Weibin and Wang, Zhiyang and He, Jie and Zhang, Hanzhi and Jiao, Licheng},
  title = {WaterGPT: Training a Large Language Model to Become a Hydrology Expert},
  journal = {Water},
  year = {2024},
  volume = {16},
  number = {21},
  pages = {3075},
  doi = {10.3390/w16213075}
}
Kostenlos starten →