What question did this study set out to answer?

The aim is to enhance reservoir storage prediction using AI and hydrological modeling methods.

November 18, 2025WaterOpen Access

AI-Based Time-Series Ensemble Approach Coupled with a Hydrological Model for Reservoir Storage Prediction in Korea

View Full Paper

Ask AI

Bookmark

Authors

AI-based approach improves reservoir storage prediction accuracy amidst seasonal flooding and inflow challenges.

The aim is to enhance reservoir storage prediction using AI and hydrological modeling methods.
Proposed an AI-based framework that incorporates hydrological models for inflow and outflow simulation.
Utilized a Bayesian Model Averaging ensemble of LSTM, GRU, and TFT models for predictions.
Analyzed prediction accuracy through Mean Absolute Error and correlation coefficients.
Achieved MAEs of 0.820%p, 1.339%p, and 1.766%p for 1-day, 2-day, and 3-day ahead predictions respectively.
Correlation coefficients reached 0.994, 0.987, and 0.980, indicating high prediction accuracy over various lead times.

Park et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

November 18, 2025WaterOpen Access

View Full Paper

Ask AI

Bookmark

Authors

AI-based approach improves reservoir storage prediction accuracy amidst seasonal flooding and inflow challenges.

The aim is to enhance reservoir storage prediction using AI and hydrological modeling methods.
Proposed an AI-based framework that incorporates hydrological models for inflow and outflow simulation.
Utilized a Bayesian Model Averaging ensemble of LSTM, GRU, and TFT models for predictions.
Analyzed prediction accuracy through Mean Absolute Error and correlation coefficients.
Achieved MAEs of 0.820%p, 1.339%p, and 1.766%p for 1-day, 2-day, and 3-day ahead predictions respectively.
Correlation coefficients reached 0.994, 0.987, and 0.980, indicating high prediction accuracy over various lead times.

Park et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark