What question did this study set out to answer?

The research aims to compare various hybrid deep learning models for predicting dam inflow under hydrological variability.

February 19, 2026Open Access

Comparative Analysis of Hybrid Deep Learning Models for Dam Inflow Prediction: LSTM-GRU, CNN-LSTM, Attention-LSTM, and Transformer Approaches

Puntos clave

The research aims to compare various hybrid deep learning models for predicting dam inflow under hydrological variability.
Utilized a 14-year dataset from Jiroft Dam in Iran
Compared four hybrid architectures: LSTM-GRU, CNN-LSTM, Attention-LSTM, and Transformer
Employed advanced validation methods including statistical tests and visual representations
LSTM-GRU achieved the best performance with 0.873 R² and 29.73 m³/s RMSE
Flow rates varied significantly with winter maxima at 391.5 m³/s and autumn minima at 56.2 m³/s
All models predicted lower peak flows with a percentage bias ranging from -14.34% to -20.86%
Precipitation and agricultural interactions emerged as key variables in forecasting

Resumen

This study offers the first comprehensive comparison among four hybrid deep learning architectures—LSTM-GRU, CNN-LSTM, Attention-LSTM, and Transformer—for multipurpose dam inflow forecasting under severe hydrological variability. The study employed a 14-year dataset (168 observations, 2010-2023) obtained from Jiroft Dam in Iran and framed with hydrological and operational parameters including precipitation, reservoir capacity, agricultural discharge, and turbine functions. The LSTM-GRU architecture yielded the best performance by attaining 0.873 R² and 29.73 m³/s root mean square error (RMSE) during the validation procedure and demonstrating the best balance among accuracy and generalizability. The model robustness was confirmed by advanced validation methods including Taylor diagrams, violin diagrams, and statistical testing (Kolmogorov-Smirnov, Ljung-Box, and Breusch-Pagan tests). Seasonal analysis revealed a seven times change in flow rates ranging across winter maxima of 391.5 m³/s and autumn minima of 56.2 m³/s. The models showed a widespread tendency to predict lower peak flows (percentage bias, PBIAS: -14.34% to -20.86%), suggesting the presence of operational safety buffers. Precipitation–agricultural interactions were identified as the key forecasting variable (importance = 0.999). The model provides real-time support for decision-making on reservoir management, flood protection, and potable water supply under changing environmental circumstances and provides a validated model for AI-accelerated water resource management.

Leer artículo completoexternamente

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo