EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Deciphering Nonlinear Hydrological Process by a Coupled Deep Learning and Physical Based Model in Southern Tibetan Plateau

Zhanliang Zhu, Xiongpeng Tang, Jianyun Zhang, Yehai Tang, Lei Liu, Chao Gao, Silong Zhang, Yanli Liu, Junliang Jin, Cuishan Liu, Bikui Zhao, Guoqing Wang

Water Resources Research · 2025-08 · 61 (8)

DOI: 10.1029/2024wr038515 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water Resources Research, online erschienen am 20.08.2025. Verfasst von Zhanliang Zhu und 11 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 91 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Interpretability of deep learning (DL) poses a significant challenge in hydrology modeling, particularly under the complex and frigid conditions of the Tibetan Plateau (TP), which further restricts its application. In this study, we developed a cascade‐style hybrid modeling framework by integrating the Variable Infiltration Capacity (VIC) model with a two‐dimensional grid long short‐term memory (termed VIC‐LSTM), and incorporated a dual‐layer probe for training and investigating non‐linear hydrological processes. Our objective was to explore the framework's potential for enhancing hydrological simulation accuracy and expanding interpretability. This framework was adopted for the Yarlung Zangbo River Basin (above the Lazi guaged station) in the TP. The results of the VIC‐LSTM demonstrated its effectiveness, achieving a simulated daily streamflow NSE of 0.78 compared to 0.69 for the VIC model during the training period. Moreover, the probe experiments, aided by remote‐sensed images, successfully deciphered the timing signals of snowmelt and glacier melt, with ablation and duration time errors within 2 weeks. The average errors for snowmelt and glacier melt were approximately 7 and 10 days, respectively. The combined spatial and temporal feature quantification indicated that snowmelt and glacier melt contributed 23.7% and 7.7% to the total streamflow, respectively. Additionally, VIC‐LSTM identified that snowmelt signals generally preceded glacier melt signals. These findings underscore the potential of VIC‐LSTM to interpret hydrological processes, increasing confidence in using DL approaches. Therefore, it offers a new perspective for quantifying water resources and understanding hydrological processes in high‐elevation, glacier‐snow coexisting basins.

Zitieren

APA

Zhu, Z., Tang, X., Zhang, J., Tang, Y., Liu, L., Gao, C., Zhang, S., Liu, Y., Jin, J., Liu, C., Zhao, B., & Wang, G. (2025). Deciphering Nonlinear Hydrological Process by a Coupled Deep Learning and Physical Based Model in Southern Tibetan Plateau. Water Resources Research, 61(8). https://doi.org/10.1029/2024wr038515

Vancouver

Zhu Z, Tang X, Zhang J, Tang Y, Liu L, Gao C, et al. Deciphering Nonlinear Hydrological Process by a Coupled Deep Learning and Physical Based Model in Southern Tibetan Plateau. Water Resources Research. 2025;61(8). doi:10.1029/2024wr038515

BibTeX
@article{Zhu2025,
  author = {Zhu, Zhanliang and Tang, Xiongpeng and Zhang, Jianyun and Tang, Yehai and Liu, Lei and Gao, Chao and Zhang, Silong and Liu, Yanli and Jin, Junliang and Liu, Cuishan and Zhao, Bikui and Wang, Guoqing},
  title = {Deciphering Nonlinear Hydrological Process by a Coupled Deep Learning and Physical Based Model in Southern Tibetan Plateau},
  journal = {Water Resources Research},
  year = {2025},
  volume = {61},
  number = {8},
  doi = {10.1029/2024wr038515}
}
Kostenlos starten →