%0 Journal Article
%T Comparison of Two Recurrent Neural Networks for Rainfall-Runoff Modeling in the Zou River Basin at Atchérigbé (Bénin)
%A Iboukoun Eli&#233
%A zer Biao
%A Oscar Houessou
%A Pierre J&#233
%A r&#244
%A me Zohou
%A Ad&#233
%A china Eric Alamou
%J Journal of Geoscience and Environment Protection
%P 167-181
%@ 2327-4344
%D 2024
%I Scientific Research Publishing
%R 10.4236/gep.2024.129009
%X Hydrological models are developed to simulate river flows over a watershed for many practical applications in the field of water resource management. The present paper compares the performance of two recurrent neural networks for rainfall-runoff modeling in the Zou River basin at Atch&#233;rigb&#233; outlet. To this end, we used daily precipitation data over the period 1988-2010 as input of the models, such as the Long Short-Term Memory (LSTM) and Recurrent Gate Networks (GRU) to simulate river discharge in the study area. The investigated models give good results in calibration (R<sup>2</sup> = 0.888, NSE = 0.886, and RMSE = 0.42 for LSTM; R<sup>2</sup> = 0.9, NSE = 0.9 and RMSE = 0.397 for GRU) and in validation (R<sup>2</sup> = 0.865, NSE = 0.851, and RMSE = 0.329 for LSTM; R<sup>2</sup> = 0.9, NSE = 0.865 and RMSE = 0.301 for GRU). This good performance of LSTM and GRU models confirms the importance of models based on machine learning in modeling hydrological phenomena for better decision-making.
%K Supervised Learning
%K Modeling
%K Zou Basin
%K Long and Short-Term Memory
%K Gated Recurrent Unit
%K Hyperparameters Optimization
%U http://www.scirp.org/journal/PaperInformation.aspx?PaperID=136353