EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting the Flow Fields in Meandering Rivers with a Deep Super-Resolution Convolutional Neural Network

Xiaohui Yan, Fu Du, Tianqi Zhang, Qian Cui, Zuhao Zhu, Ziming Song

Water · 28.01.2024 · 16 (3) · 425

DOI: 10.3390/w16030425 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water, online erschienen am 28.01.2024. Verfasst von Xiaohui Yan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Open Research Fund Program of Shandong Key Laboratory of Eco-Environmental Science for the Yellow River Delta (Shandong University of Aeronautics), Guangxi Key Laboratory of Beibu Gulf Marine Resources, Environment and Sustainable Development, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The hydrodynamic model, based on the strict conservation of momentum and continuity equations, can accurately simulate the distribution of a flow field. However, significant computing time and storage space requirements limit real-time prediction. Machine learning is well known for its fast computing speed and powerful learning ability, but its accuracy depends on an abundance of training data, hindering its wider use in locations without sufficient measurements. Application restrictions in data-deficient areas can be addressed through transfer learning, provided that two areas share common characteristics. In this study, a machine learning method based on a deep super-resolution convolutional neural network (DSRCNN) and transfer learning is proposed, validated, and applied to model two bend flows and one realistic test case. Firstly, the hydrodynamic model was established and validated against measured data. The validated model was considered to have the ability to generate real data and was used to generate a comprehensive data set for training and validating the machine learning model. Three different methods were compared and tested, with Realizable k-ε performing better than the others in predicting the outer bank flow distribution. DSRCNN was compared to a plain SRCNN (PSRCNN), as well as Bilinear, Nearest, and Bicubic methods, and the results showed that DSRCNN had the best performance. We compared Raw, RT, and TL methods, finding that the TL method performed the best overall. Therefore, the research results showed that the developed super-resolution convolutional neural network can provide more reliable predications and serve as an ideal tool for simulating flow field distribution in bends.

Förderung

  • Open Research Fund Program of Shandong Key Laboratory of Eco-Environmental Science for the Yellow River Delta (Shandong University of Aeronautics)
  • Guangxi Key Laboratory of Beibu Gulf Marine Resources, Environment and Sustainable Development
  • National Natural Science Foundation of China
  • National Key Research and Development Program of China

Zitieren

APA

Yan, X., Du, F., Zhang, T., Cui, Q., Zhu, Z., & Song, Z. (2024). Predicting the Flow Fields in Meandering Rivers with a Deep Super-Resolution Convolutional Neural Network. Water, 16(3), 425. https://doi.org/10.3390/w16030425

Vancouver

Yan X, Du F, Zhang T, Cui Q, Zhu Z, Song Z. Predicting the Flow Fields in Meandering Rivers with a Deep Super-Resolution Convolutional Neural Network. Water. 2024;16(3):425. doi:10.3390/w16030425

BibTeX
@article{Yan2024,
  author = {Yan, Xiaohui and Du, Fu and Zhang, Tianqi and Cui, Qian and Zhu, Zuhao and Song, Ziming},
  title = {Predicting the Flow Fields in Meandering Rivers with a Deep Super-Resolution Convolutional Neural Network},
  journal = {Water},
  year = {2024},
  volume = {16},
  number = {3},
  pages = {425},
  doi = {10.3390/w16030425}
}
Kostenlos starten →