Adaptive neuro-fuzzy inference system coupled with shuffled frog leaping algorithm for predicting river streamflow time series

No Thumbnail Available
Mohammadi B.
Linh N.T.T.
Pham Q.B.
Ahmed A.N.
Vojtekov� J.
Guan Y.
Abba S.I.
El-Shafie A.
Journal Title
Journal ISSN
Volume Title
Taylor and Francis Ltd.
Research Projects
Organizational Units
Journal Issue
Accurate runoff forecasting plays a key role in catchment water management and water resources system planning. To improve the prediction accuracy, one needs to strive to develop a reliable and accurate forecasting model for streamflow. In this study, the novel combination of the adaptive neuro-fuzzy inference system (ANFIS) model with the shuffled frog-leaping algorithm (SFLA) is proposed. Historical streamflow data of two different rivers were collected to examine the performance of the proposed model. To evaluate the performance of the proposed ANFIS-SFLA model, six different scenarios for the model input�output architecture were investigated. The results show that the proposed ANFIS-SFLA model (R2 =�0.88; NS�=�0.88; RMSE�=�142.30 (m3/s); MAE�=�88.94 (m3/s); MAPE�=�35.19%) significantly improved the forecasting accuracy and outperformed the classic ANFIS model (R2 =�0.83; NS�=�0.83; RMSE�=�167.81; MAE�=�115.83 (m3/s); MAPE�=�45.97%). The proposed model could be generalized and applied in different rivers worldwide. � 2020 IAHS.
Catchments; Forecasting; Fuzzy neural networks; Fuzzy systems; Inference engines; Rivers; Stream flow; Water management; Adaptive neuro-fuzzy inference system; Forecasting accuracy; Forecasting modeling; Model inputs; Prediction accuracy; Runoff forecasting; Shuffled frog leaping algorithm (SFLA); Water resources systems; Fuzzy inference; accuracy assessment; algorithm; fuzzy mathematics; prediction; river flow; runoff; streamflow; time series; Anura