Zhao et al. (2025) Watershed Runoff Simulation and Prediction Based on BMA Coupled SWAT-LSTM Model

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Hydrology
• Year: 2025
• Date: 2025-11-24
• Authors: Wenju Zhao, Yongwei Hao, Yongming Zhang, Haiying Yu, Xing Li
• DOI: 10.3390/hydrology12120312

Research Groups

[Not explicitly mentioned in the provided text.]

Short Summary

This study develops and evaluates a SWAT-LSTM-BMA coupled model to improve runoff prediction accuracy, particularly in regions prone to extreme hydrological events, finding it to be the optimal model for the Zuli River Basin with significant accuracy improvements and predicting a future decrease in annual runoff.

Objective

• To improve runoff prediction accuracy and parameter determination in regions frequently experiencing extreme hydrological events by developing and evaluating a SWAT-LSTM-BMA coupled model, and to predict future runoff for the Zuli River Basin.

Study Configuration

• Spatial Scale: Zuli River Basin
• Temporal Scale: Historical period (for model calibration and validation) and future prediction period (2025 to 2030)

Methodology and Data

• Models used: SWAT (Soil and Water Assessment Tool), LSTM (Long Short-Term Memory), SWAT-LSTM (coupled), SWAT-LSTM-BMA (coupled using Bayesian Model Averaging)
• Data sources: Digital elevation data, land use data, soil type data, meteorological data

Main Results

• The SWAT-LSTM-BMA coupled model is identified as the optimal runoff prediction model for the Zuli River Basin.
• Compared to the standalone SWAT model and the SWAT-LSTM model, the SWAT-LSTM-BMA model showed systematic improvements in simulation accuracy:
  • During the calibration period: R² increased by 8–12%, NSE increased by 9–13%, and MSE decreased by 14–30%.
  • During the validation period: R² increased by 10–12%, NSE increased by 10–14%, and MSE decreased by 16–31%.
• Based on future climate data, the annual runoff of the Zuli River Basin is predicted to decrease by 12–15% between 2025 and 2030 compared to the historical period.

Contributions

• Proposes an effective coupling framework (SWAT-LSTM-BMA) that significantly enhances the accuracy of runoff prediction.
• Provides a reliable theoretical foundation and technological assistance for understanding the evolution of extreme hydrological events and for water resource management in basins.

Funding

[Not mentioned in the provided text.]

Citation

@article{Zhao2025Watershed,
  author = {Zhao, Wenju and Hao, Yongwei and Zhang, Yongming and Yu, Haiying and Li, Xing},
  title = {Watershed Runoff Simulation and Prediction Based on BMA Coupled SWAT-LSTM Model},
  journal = {Hydrology},
  year = {2025},
  doi = {10.3390/hydrology12120312},
  url = {https://doi.org/10.3390/hydrology12120312}
}