您好,欢迎访问中国农业科学院 机构知识库!

A visualizable deep learning model for multiscale precipitation-driven karst spring discharge

文献类型: 外文期刊

作者: Hao, Huiqing 1 ; Hao, Yonghong 2 ; Ma, Chunmei 3 ; Duan, Limin 4 ; Yan, Xiping 3 ; Wang, Qi 5 ; Liu, Yan 6 ; Zhang, Wenrui 7 ; Yeh, Tian-Chyi Jim 8 ;

作者机构: 1.Tianjin Normal Univ, Fac Geog, Tianjin 300387, Peoples R China

2.Tianjin Normal Univ, Tianjin Key Lab Water Resources & Environm, Tianjin 300387, Peoples R China

3.Tianjin Normal Univ, Sch Comp & Informat Engn, Tianjin 300387, Peoples R China

4.Inner Mongolia Agr Univ, Coll Water Conservancy & Civil Engn, Hohhot 010018, Peoples R China

5.Univ South Carolina, Dept Math, Columbia, SC 29208 USA

6.Tianjin Normal Univ, Sch Math Sci, Tianjin 300387, Peoples R China

7.Chinese Acad Agr Sci, Inst Grassland Res, Hohhot 010010, Peoples R China

8.Univ Arizona, Dept Hydrol & Atmospher Sci, Tucson, AZ 85721 USA

关键词: Karst spring discharge; Spatiotemporal explainability; Hybrid deep learning model; Multiscale transformer; Visual attention; Graph neural networks

期刊名称:JOURNAL OF HYDROLOGY ( 影响因子:6.3; 五年影响因子:6.9 )

ISSN: 0022-1694

年卷期: 2025 年 657 卷

页码:

收录情况: SCI

摘要: Groundwater from karst aquifers provides drinking water for 25% of the world's population. However, the complexity of karst terrain and karst aquifer heterogeneity hinders comprehensively understanding and predicting karst hydrological processes. This study proposes a deep learning model coupling a multiscale transformer (TSF) with a direction-constrained graph neural network (GNN) for forecasting karst spring discharge. The TSF deciphers the time-dependent patterns between precipitation and spring discharge, while the directed GNN tracks surface water convergence and the groundwater diffusion. Applying the model to Shentou Spring in northern China, we discover that visualization of attention weights in the TSF can reveal the multiscale temporal dependence of spring discharge on precipitation through successive transmission over a 12-month lead time, while the memory effect of transmitted information decays over time. Moreover, we find that the intra-patch attention weights at annual and seasonal scales follow normal distributions. The variability of spring discharge is most profound on an annual scale in the year's first half. At the seasonal scale, the variability of spring discharge driven by precipitation is the most significant in the summer and the slightest in the winter. On the other hand, visualization of edge weights in the directed GNN highlights the spatial dependence of spring discharge, depicting surface water convergence and groundwater diffusion. In addition, the groundwater flow field-based graph enables the GNN to yield the best predictive performance compared to the complete and information flow graph.

  • 相关文献
作者其他论文 更多>>