Download

Download Full Text (164 KB)

Description

Predicting streamflow with process-based models is challenging due to parameter uncertainties and streamflow complexity. Data-driven approaches provide viable alternatives without requiring physical process representation. This study introduces a hybrid deep learning framework, CNN-GRU-BiLSTM, for daily streamflow prediction. This model integrates Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and Bidirectional Long ShortTerm Memory (BiLSTM) networks to leverage their complementary strengths. When applied to the Neuse River Basin (NRB) (North Carolina, USA), the proposed model achieved strong predictive performance, yielding a root mean square (RMSE) of 11.8 m³/s (compared to an average streamflow of 132.7 m³/s), and a mean absolute error (MAE) of 8.7 m³/s, and a Nush-Sutcliffe efficiency (NSE) of 0.994 for the testing dataset. Similar performance trends were observed in the training and validation phases. A comparative analysis against seven other deep learning and hybrid models of similar complexity highlighted the outstanding performance of the CNN-GRU-BiLSTM model across all flood events. Furthermore, its stability, robustness, and transferability were evaluated in a seasonal dataset, as well as peak floods and two locations along the river. These findings underscore the potential of hybrid deep learning models and reinforce the effectiveness of integrating multiple data-driven techniques for streamflow prediction.

Publication Date

4-1-2025

Keywords

Time series data, Deep-learning, hybrid models, transferable model

Utilizing Hybrid Deep Learning Models for Streamflow Prediction

Share

COinS