EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A New Water Temperature Simulation Method Based on Air Temperature–Surface Solar Radiation–Recurrent Neural Network Coupling

Zhe Wang, Li Fang, Taotao Li, Lin Wei, Feng Yan

Water · 19.05.2026 · 18 (10) · 1223

DOI: 10.3390/w18101223 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water, online erschienen am 19.05.2026. Verfasst von Zhe Wang und 4 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program Funded Project, Core Technology Breakthrough Project of Power Construction Corporation Limited.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Water temperature (WT) is a vital parameter influencing river ecosystems. Air temperature (AT) is usually regarded as a major input in WT simulation, but surface solar radiation (SSR) is often overlooked in current statistical methods. In this study, a new WT simulation method is proposed based on a Recurrent Neural Network (RNN) that integrates AT and SSR. The AT-SSR-RNN coupling model is applied in the lower reaches of the Yangtze River. The results show the following: (i) The annual mean WT in the lower reaches of the Yangtze River is 18.8 °C, and the peak WT usually occurs in August. (ii) The proposed model demonstrates robust simulation performance, yielding a Nash–Sutcliffe Efficiency (NSE) of 0.9100, Root Mean Square Error (RMSE) of 2.08 °C, Mean Absolute Error (MAE) of 1.65 °C, and Symmetric Mean Absolute Percentage Error (SMAPE) of 9.61%. (iii) Incorporation of SSR substantially enhances simulation accuracy, with NSE increasing by 8.2% and RMSE decreasing by 24.6%, MAE by 30.4%, and SMAPE by 33.1% compared to the AT-only model. (iv) Compared with the Back-Propagation Neural Network (BPNN) and Random Forest (RF), the RNN achieves superior performance with the highest NSE (0.9100) and lowest error indicators (RMSE: 2.08 °C, SMAPE: 9.61%).

Förderung

  • National Key R&D Program Funded Project
  • Core Technology Breakthrough Project of Power Construction Corporation Limited

Zitieren

APA

Wang, Z., Fang, L., Li, T., Wei, L., & Yan, F. (2026). A New Water Temperature Simulation Method Based on Air Temperature–Surface Solar Radiation–Recurrent Neural Network Coupling. Water, 18(10), 1223. https://doi.org/10.3390/w18101223

Vancouver

Wang Z, Fang L, Li T, Wei L, Yan F. A New Water Temperature Simulation Method Based on Air Temperature–Surface Solar Radiation–Recurrent Neural Network Coupling. Water. 2026;18(10):1223. doi:10.3390/w18101223

BibTeX
@article{Wang2026,
  author = {Wang, Zhe and Fang, Li and Li, Taotao and Wei, Lin and Yan, Feng},
  title = {A New Water Temperature Simulation Method Based on Air Temperature–Surface Solar Radiation–Recurrent Neural Network Coupling},
  journal = {Water},
  year = {2026},
  volume = {18},
  number = {10},
  pages = {1223},
  doi = {10.3390/w18101223}
}
Kostenlos starten →