EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Task Learning Framework for Reservoir Water Temperature Field Prediction Using Modal Decomposition and Federated Learning

Shushan Liu, Di Zhang, Junqiang Lin, Boran Zhu, Youkun Li, Qidong Peng, Tiantian Jin, Jun Yan

Sustainability · 10.11.2026 · 18 (22) · 11450

DOI: 10.3390/su182211450 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sustainability, online erschienen am 10.11.2026. Verfasst von Shushan Liu und 7 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, China Institute of Water Resources and Hydropower Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reservoir thermal stratification affects withdrawal temperatures and downstream aquatic ecosystems, making water temperature prediction important for sustainable reservoir operation. However, predicting two-dimensional water temperature fields across different operating conditions remains challenging. This study proposes a framework integrating proper orthogonal decomposition (POD), mutual information, dual-channel BiLSTM, bidirectional residual cross-attention, multi-task learning, and personalized federated learning. POD reduces field dimensionality, while multi-task regression heads directly predict modal coefficients for different forecast days. To account for differences among operating conditions, feature-extraction networks remain local, and only regression-network parameters are aggregated. Experiments were conducted using EFDC-simulated temperature fields from 75 operating conditions of Wudongde Reservoir. The model achieved MAE and RMSE values of 0.120 °C and 0.183 °C for 2-day forecasts and 0.314 °C and 0.449 °C for 10-day forecasts, respectively. Compared with full-model aggregation, theoretical parameter communication was reduced by 96.29%, with slightly higher prediction errors. The predicted temperature fields may support the assessment of selective-withdrawal conditions and downstream ecological temperature requirements, contributing to sustainable reservoir management.

Förderung

  • National Key R&D Program of China
  • China Institute of Water Resources and Hydropower Research

Zitieren

APA

Liu, S., Zhang, D., Lin, J., Zhu, B., Li, Y., Peng, Q., Jin, T., & Yan, J. (2026). Multi-Task Learning Framework for Reservoir Water Temperature Field Prediction Using Modal Decomposition and Federated Learning. Sustainability, 18(22), 11450. https://doi.org/10.3390/su182211450

Vancouver

Liu S, Zhang D, Lin J, Zhu B, Li Y, Peng Q, et al. Multi-Task Learning Framework for Reservoir Water Temperature Field Prediction Using Modal Decomposition and Federated Learning. Sustainability. 2026;18(22):11450. doi:10.3390/su182211450

BibTeX
@article{Liu2026,
  author = {Liu, Shushan and Zhang, Di and Lin, Junqiang and Zhu, Boran and Li, Youkun and Peng, Qidong and Jin, Tiantian and Yan, Jun},
  title = {Multi-Task Learning Framework for Reservoir Water Temperature Field Prediction Using Modal Decomposition and Federated Learning},
  journal = {Sustainability},
  year = {2026},
  volume = {18},
  number = {22},
  pages = {11450},
  doi = {10.3390/su182211450}
}
Kostenlos starten →