EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Deep U-Net-ConvLSTM Framework with Hydrodynamic Model for Basin-Scale Hydrodynamic Prediction

Ao Li, Wanshun Zhang, Xiao Zhang, Gang Chen, Xin Liu, Anna Jiang, Feng Zhou, Hong Peng

Water · 20.02.2024 · 16 (5) · 625

DOI: 10.3390/w16050625 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water, online erschienen am 20.02.2024. Verfasst von Ao Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China, the National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional hydrodynamic models face the significant challenge of balancing the demands of long prediction spans and precise boundary conditions, large computational areas, and low computational costs when attempting to rapidly and accurately predict the nonlinear spatial and temporal characteristics of fluids at the basin scale. To tackle this obstacle, this study constructed a novel deep learning framework with a hydrodynamic model for the rapid spatiotemporal prediction of hydrodynamics at the basin scale, named U-Net-ConvLSTM. A validated high-fidelity hydrodynamic mechanistic model was utilized to build a 20-year hydrodynamic indicator dataset of the middle and lower reaches of the Han River for the training and validation of U-Net-ConvLSTM. The findings indicate that the R2 value of the model surpassed 0.99 when comparing the single-step prediction results with the target values. Additionally, the required computing time fell by 62.08% compared with the hydrodynamic model. The ablation tests demonstrate that the U-Net-ConvLSTM framework outperforms other frameworks in terms of accuracy for basin-scale hydrodynamic prediction. In the multi-step-ahead prediction scenarios, the prediction interval increased from 1 day to 5 days, while consistently maintaining an R2 value above 0.7, which demonstrates the effectiveness of the model in the missing boundary conditions scenario. In summary, the U-Net-ConvLSTM framework is capable of making precise spatiotemporal predictions in hydrodynamics, which may be considered a high-performance computational solution for predicting hydrodynamics at the basin scale.

Förderung

  • the National Natural Science Foundation of China
  • the National Key Research and Development Program of China

Zitieren

APA

Li, A., Zhang, W., Zhang, X., Chen, G., Liu, X., Jiang, A., Zhou, F., & Peng, H. (2024). A Deep U-Net-ConvLSTM Framework with Hydrodynamic Model for Basin-Scale Hydrodynamic Prediction. Water, 16(5), 625. https://doi.org/10.3390/w16050625

Vancouver

Li A, Zhang W, Zhang X, Chen G, Liu X, Jiang A, et al. A Deep U-Net-ConvLSTM Framework with Hydrodynamic Model for Basin-Scale Hydrodynamic Prediction. Water. 2024;16(5):625. doi:10.3390/w16050625

BibTeX
@article{Li2024,
  author = {Li, Ao and Zhang, Wanshun and Zhang, Xiao and Chen, Gang and Liu, Xin and Jiang, Anna and Zhou, Feng and Peng, Hong},
  title = {A Deep U-Net-ConvLSTM Framework with Hydrodynamic Model for Basin-Scale Hydrodynamic Prediction},
  journal = {Water},
  year = {2024},
  volume = {16},
  number = {5},
  pages = {625},
  doi = {10.3390/w16050625}
}
Kostenlos starten →