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

Summary, in English

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.

• Author: Babak Mohammadi; Nguyen Thi Thuy Linh; Quoc Bao Pham; Ali Najah Ahmed; Jana Vojteková; Yiqing Guan; S. I. Abba; Ahmed El-Shafie
• Publishing year: 2020-07-26
• Language: English
• Pages: 1738-1751
• Publication/Series: Hydrological Sciences Journal
• Volume: 65
• Issue: 10
• Links: http://dx.doi.org/10.1080/02626667.2020.1758703
• Document type: Journal article
• Publisher: Taylor & Francis
• Topic: Oceanography, Hydrology, Water Resources
• Keywords: adaptive neuro-fuzzy inference system (ANFIS); estimation; shuffled frog leaping algorithm (SFLA); Streamflow; time series models
• Status: Published
• ISBN/ISSN/Other: ISSN: 0262-6667