EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Characteristic‐Aligned Control‐Volume Physics‐Informed Neural Network for Flood‐Wave Propagation and Roughness Estimation

Ziyan Lu, Tao Wang, Jingjing Duan, Yongnan Zhu, Xusheng He, Anjun Deng, Zhongjing Wang

Water Resources Research · 2026-10 · 62 (10)

DOI: 10.1029/2026wr043613 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water Resources Research, online erschienen am 11.10.2026. Verfasst von Ziyan Lu und 6 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Physics‐informed neural networks (PINNs) provide a promising framework for river hydrodynamic simulation and parameter inversion under sparse observations. However, spatial heterogeneity in channel geometry and roughness causes strong variations in flood‐wave propagation and parameter sensitivity, challenging local conservation and joint state‐parameter estimation. This study proposes a Characteristic‐aligned Control‐volume Physics‐Informed Neural Network for Roughness Estimation (CC‐PINN‐RE). It constructs dynamic diamond‐shaped space‐time control volumes from local characteristic speeds of the Saint‐Venant equations, enforces mass and momentum conservation in integral form, and combines adaptive control‐volume management with local‐sensitivity‐weighted roughness regularization. The method is evaluated on three one‐dimensional channel cases of increasing complexity against strong‐form PINN‐RE and fixed‐control‐volume cvPINN‐RE. CC‐PINN‐RE achieves the lowest errors in eight of nine relative metrics for water depth, discharge, and roughness. In Case 3, where channel width, bed slope, and roughness vary spatially, it reduces the corresponding errors by 57.0%, 82.2%, and 57.3% relative to PINN‐RE and reduces the maximum absolute error in peak water depth by 69.7%. Ablation experiments with three random seeds support the contributions of the three proposed components. Observation‐deployment experiments show that increasing the number of monitoring stations is generally more effective than increasing temporal sampling frequency at individual stations. Under 0%–2% observational noise in Case 3, the model remains stable. These results indicate that CC‐PINN‐RE provides a physically consistent framework for integrating characteristic propagation, local conservation, and parameter inversion, offering a useful basis for joint hydrodynamic reconstruction and spatially varying roughness estimation in heterogeneous river channels.

Förderung

  • National Key Research and Development Program of China

Zitieren

APA

Lu, Z., Wang, T., Duan, J., Zhu, Y., He, X., Deng, A., & Wang, Z. (2026). Characteristic‐Aligned Control‐Volume Physics‐Informed Neural Network for Flood‐Wave Propagation and Roughness Estimation. Water Resources Research, 62(10). https://doi.org/10.1029/2026wr043613

Vancouver

Lu Z, Wang T, Duan J, Zhu Y, He X, Deng A, et al. Characteristic‐Aligned Control‐Volume Physics‐Informed Neural Network for Flood‐Wave Propagation and Roughness Estimation. Water Resources Research. 2026;62(10). doi:10.1029/2026wr043613

BibTeX
@article{Lu2026,
  author = {Lu, Ziyan and Wang, Tao and Duan, Jingjing and Zhu, Yongnan and He, Xusheng and Deng, Anjun and Wang, Zhongjing},
  title = {Characteristic‐Aligned Control‐Volume Physics‐Informed Neural Network for Flood‐Wave Propagation and Roughness Estimation},
  journal = {Water Resources Research},
  year = {2026},
  volume = {62},
  number = {10},
  doi = {10.1029/2026wr043613}
}
Kostenlos starten →