EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explicit Water Balance Constraints for Trustworthy Graph Neural Network Flood Forecasting

Yuqi Chen, Ruixi Huang, Yue Tang, Hao Wang, Tong Zhou, Junlin Fan, Yin Long, Tehseen Zia

Applied Sciences · 15.05.2026 · 16 (10) · 4963

DOI: 10.3390/app16104963 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 15.05.2026. Verfasst von Yuqi Chen und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the International Scientific and Technological Cooperation Projects of Sichuan Province, Central Government Guides Local Projects of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Although Graph Neural Networks (GNNs) are widely regarded as an ideal tool for capturing spatial dependencies in river basins, their effectiveness in hydrological forecasting is severely challenged by a topology paradox: under a purely data-driven paradigm, GNNs fail to spontaneously learn physical laws, generating predictions that lack physical interpretability and frequently violate mass conservation. To address this fundamental problem, this paper proposes a physics-informed graph learning framework integrated with an explicit, differentiable water balance constraint (WB-GNN). By reconstructing the continuity equation into a differentiable loss function, we directly embed physical conservation as a strong inductive bias into the neural network’s training objective. We comprehensively evaluated the model on two large-sample datasets (LamaH-CE and CAMELS) against state-of-the-art baselines, including EA-LSTM and unconstrained Pure-GNN. Quantitative results demonstrate that the proposed physical constraint successfully awakens the potential of river network topology. On the LamaH-CE dataset, WB-GNN achieved a Nash-Sutcliffe Efficiency (NSE) of 0.86 and a Root Mean Square Error (RMSE) of 9.2 m3/s, outperforming both the domain-specific EA-LSTM (NSE: 0.83) and the unconstrained Pure-GNN (NSE: 0.74). Crucially, the introduction of the differentiable constraint reduced the Physical Inconsistency Ratio (PIR) by an order of magnitude-from 39.8% in the unconstrained model to just 4.3%. Similar robust improvements were validated across the highly heterogeneous CAMELS dataset. These quantifiable results confirm that the proposed method not only achieves superior forecasting accuracy but also fundamentally guarantees physical trustworthiness, making it highly robust for critical decision-making in extreme flood events.

Förderung

  • the International Scientific and Technological Cooperation Projects of Sichuan Province
  • Central Government Guides Local Projects of China

Zitieren

APA

Chen, Y., Huang, R., Tang, Y., Wang, H., Zhou, T., Fan, J., Long, Y., & Zia, T. (2026). Explicit Water Balance Constraints for Trustworthy Graph Neural Network Flood Forecasting. Applied Sciences, 16(10), 4963. https://doi.org/10.3390/app16104963

Vancouver

Chen Y, Huang R, Tang Y, Wang H, Zhou T, Fan J, et al. Explicit Water Balance Constraints for Trustworthy Graph Neural Network Flood Forecasting. Applied Sciences. 2026;16(10):4963. doi:10.3390/app16104963

BibTeX
@article{Chen2026,
  author = {Chen, Yuqi and Huang, Ruixi and Tang, Yue and Wang, Hao and Zhou, Tong and Fan, Junlin and Long, Yin and Zia, Tehseen},
  title = {Explicit Water Balance Constraints for Trustworthy Graph Neural Network Flood Forecasting},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {10},
  pages = {4963},
  doi = {10.3390/app16104963}
}
Kostenlos starten →