EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

River Surface Velocity and Discharge Estimation Using Optical Flow and Unlabeled Physics-Informed Neural Networks

Zhongyu Shu iD, Yubo Gao iD, Guo Zhang iD, Zihan Xu iD, Jianping Wang iD

Sensors · 29.05.2026 · 26 (11) · 3448

DOI: 10.3390/s26113448 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.05.2026. Verfasst von Zhongyu Shu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, 'Yunnan Xingdian Talents Support Plan' Project, ‘Yunnan Xingdian Talents Support Plan’ Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Quantifying river surface velocity and discharge is essential for flood control and mitigation. Traditional contact measurement methods are capable of providing precise results, yet they demand considerable manpower and material resources and face implementation challenges in flood seasons. Image velocimetry methods have attracted extensive attention due to their low cost, simplicity in operation, and safety. However, most of them lack a physical basis and interpretability. This paper introduces a river flow estimation algorithm combined with Physics-Informed Neural Networks (PINNs). The introduction of the convection–diffusion equation based on optical flow enables the model to better fit the flow characteristics of water and provides stronger physical support for the measurement results. The adoption of this equation as the loss function and the introduction of multiple scenarios eliminate the need for labeled data in the PINNs training process. The experimental results in both artificial and natural river channels demonstrate that the relative errors of the discharge measured by the proposed method are 0.66% and −1.75%, and the relative errors of the mean velocity are 0.64% and −2.33%. Compared with other methods, the proposed method exhibits superior performance.

Schlagwörter

Stichwörter der Autor:innen

convection–diffusion equationphysics-informed neural networksriver dischargeriver surface velocity

Autor:innen und Institutionen

  • Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China.
  • School of Metallurgical and Ecological Engineering, University of Science and Technology Beijing, Beijing 100083, China.

ORCID-Profile: Zhongyu Shu, Yubo Gao, Guo Zhang, Zihan Xu, Jianping Wang

Förderung

  • National Natural Science Foundation of China
  • 'Yunnan Xingdian Talents Support Plan' Project
  • ‘Yunnan Xingdian Talents Support Plan’ Project

Zitieren

APA

Shu, Z., Gao, Y., Zhang, G., Xu, Z., & Wang, J. (2026). River Surface Velocity and Discharge Estimation Using Optical Flow and Unlabeled Physics-Informed Neural Networks. Sensors, 26(11), 3448. https://doi.org/10.3390/s26113448

Vancouver

Shu Z, Gao Y, Zhang G, Xu Z, Wang J. River Surface Velocity and Discharge Estimation Using Optical Flow and Unlabeled Physics-Informed Neural Networks. Sensors. 2026;26(11):3448. doi:10.3390/s26113448

BibTeX
@article{Shu2026,
  author = {Shu, Zhongyu and Gao, Yubo and Zhang, Guo and Xu, Zihan and Wang, Jianping},
  title = {River Surface Velocity and Discharge Estimation Using Optical Flow and Unlabeled Physics-Informed Neural Networks},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3448},
  doi = {10.3390/s26113448}
}
Kostenlos starten →