Abstract:
In recent years, the success of deep learning in many diferent felds of Engineering has attracted attention. Basefow sepa ration is one of the Engineering problems which remains difcult due to diferent hydro-climatic circumstances. In this
study, we proposed a hybrid basefow prediction model by combining analytical methods and deep learning algorithms. Six
analytical methods were chosen and their performance was compared by diferent metrics. Basefow-Lyne and Hollick algo rithm (BFLOW-LHA) outperforms the others in terms of R2
, Mean Absolute Error (MAE), BIAS, Nash–Sutclife Efciency
(NSE), and Root Mean Squared Error (RMSE) metrics. The proposed model was trained using streamfow and basefow data
generated by the BFLOW-LHA with the Dawa Melka Guba dataset and then tested on prediction for the basin's remaining
three watersheds. The experimental results show that the proposed model improves the prediction of basefow as compared
with BFLOW-LHA and can be used for watersheds with similar characteristics
