HYDRA-LSTM-GRU: Self-Attention-Enhanced RainfallRunoff Modelling for Indian River Basins

Abstract

Floods are unpredictable natural disasters, often triggered by extreme weather conditions, particularly in countries like India. This study utilises machine learning to predict runoff, with a focus on attention-based models, including Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures. We compare Attentional LSTM, PCAbased LSTM, Self-Attention LSTM, and Self-Attentional GRU models across various window lengths (1, 7, 14, and 30 days). The Attentional LSTM model consistently outperforms others, achieving the lowest Mean Squared Error (MSE=0.000476) and Mean Absolute Error (MAE=0.015475) while attaining the highest Nash-Sutcliffe Efficiency (NSE=0.978). A 14-day window size provides the best balance between predictive accuracy and computational efficiency. While other attentionbased models, such as the Self-Attentional GRU (MSE=0.000654, MAE=0.018878, NSE=0.970), perform well, simpler models without attention mechanisms show significantly lower accuracy. Additionally, incorporating Principal Component Analysis (PCA) does not enhance performance, as the PCA-Based Attention LSTM (MSE= 0.000855, MAE= 0.022152, NSE=0.961). The model underperforms compared to the Attentional LSTM. Explainable AI (XAI) techniques such as LIME are used to analyse model behaviour, highlighting the importance of attention mechanisms in improving time-series predictions for hydrological applications. 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).