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

Document Type

Article

Publication Date

7-26-2020

Abstract

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 (R-2= 0.88; NS = 0.88; RMSE = 142.30 (m(3)/s); MAE = 88.94 (m(3)/s); MAPE = 35.19%) significantly improved the forecasting accuracy and outperformed the classic ANFIS model (R-2= 0.83; NS = 0.83; RMSE = 167.81; MAE = 115.83 (m(3)/s); MAPE = 45.97%). The proposed model could be generalized and applied in different rivers worldwide.

Keywords

Streamflow, Estimation, Time series models, Adaptive neuro-fuzzy inference system (ANFIS), Shuffled frog leaping algorithm (SFLA)

Divisions

sch_civ

Publication Title

Hydrological Sciences Journal-Journal des Sciences Hydrologiques

Volume

65

Issue

10

Publisher

Taylor & Francis

Publisher Location

2-4 PARK SQUARE, MILTON PARK, ABINGDON OR14 4RN, OXON, ENGLAND

This document is currently not available here.

Share

COinS