Enhanced streamflow forecasting using hybrid modelling integrating glacio-hydrological outputs, deep learning and wavelet transformation

Abstract

Abstract Understanding snow and ice melt dynamics is vital for flood risk assessment and effective water resource management in populated river basins sourced in inaccessible high-mountains. This study provides an AI-enabled hybrid approach integrating glacio-hydrological model outputs (GSM-SOCONT), with different machine learning and deep learning techniques framed as alternative ‘computational scenarios, leveraging both physical processes and data-driven insights for enhanced predictive capabilities. The standalone deep learning model (CNN-LSTM), relying solely on meteorological data, outperformed its counterpart machine learning and glacio-hydrological model equivalents. Hybrid models (CNN-LSTM1 to CNN-LSTM15) were trained using meteorological data augmented with glacio-hydrological model outputs representing ice and snow-melt contributions to streamflow. The hybrid model (CNN-LSTM14), using only glacier-derived features, performed best with high NSE (0.86), KGE (0.80), and R (0.93) values during calibration, and the highest NSE (0.83), KGE (0.88), R (0.91), and lowest RMSE (892) and MAE (544) during validation. Finally, a multi-scale analysis using different feature permutations was explored using wavelet transformation theory, integrating these into the final hybrid model (CNN-LSTM19), which significantly enhances predictive accuracy, particularly for high-flow events, as evidenced by improved NSE (from 0.83 to 0.97) and reduced RMSE (from 892 to 442) during validation. The comparative analysis illustrates how AI-enhanced hydrological models improve the accuracy of runoff forecasting and provide more reliable and actionable insights for managing water resources and mitigating flood risks - despite the paucity of direct measurements.