What question did this study set out to answer?

The aim is to improve accuracy in forecasting reservoir water levels using a novel hybrid model integrating SARIMA and GRU.

March 15, 2026Open Access

A Hybrid Model of SARIMA and GRU in Water Level Forecasting: Case Study in Ankhe Reservoir, Vietnam

Key Points

The aim is to improve accuracy in forecasting reservoir water levels using a novel hybrid model integrating SARIMA and GRU.
Developed a hybrid model combining SARIMA and GRU for forecasting water levels.
Embedded statistical components like seasonal buffers and trend differencing gates into GRU units.
Evaluated model performance on An Khe reservoir data using metrics like MAE, MSE, and RMSE.
The SE-GRU model achieved a mean absolute error (MAE) of 0.001, mean squared error (MSE) of 0.014, and root mean squared error (RMSE) of 0.041.
Outperformed standalone SARIMA, GRU, and other baseline models in forecasting accuracy.
Demonstrated effectiveness for capturing both linear and nonlinear patterns in water level fluctuations.

Abstract

Reservoir water levels exhibit significant irregular fluctuations due to climate change and intensified water resource exploitation. To improve forecasting accuracy, this study introduces SARIMA-Embedded GRU (SE-GRU), a novel hybrid model that directly embeds statistical time-series components-seasonal buffers, trend differencing gates, and ARMA structures into GRU recurrent units. Unlike conventional two-stage hybrid methods, SE-GRU simultaneously captures linear statistical patterns and nonlinear dependencies through end-to-end optimization, enhancing both accuracy and interpretability. Evaluated on An Khe reservoir data, the proposed model achieves superior performance (MAE = 0.001, MSE = 0.014, RMSE = 0.041), outperforming standalone SARIMA, GRU, and other baseline models, demonstrating the effectiveness of integrated architectural design for reservoir water level forecasting.

AI से पूछें

Bookmark

View Full Paper