Cover Image

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

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-fuzz...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohammadi, Babak, Linh, Nguyen Thi Thuy, Pham, Quoc Bao, Ahmed, Ali Najah, Vojtekova, Jana, Guan, Yiqing, Abba, S., El-Shafie, Ahmed
Format: Article
Published: Taylor & Francis 2020
Subjects:
TA Engineering (General). Civil engineering (General)
Online Access:http://eprints.um.edu.my/37621/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.37621
record_format eprints
spelling my.um.eprints.376212023-03-08T02:46:12Z http://eprints.um.edu.my/37621/ Adaptive neuro-fuzzy inference system coupled with shuffled frog leaping algorithm for predicting river streamflow time series Mohammadi, Babak Linh, Nguyen Thi Thuy Pham, Quoc Bao Ahmed, Ali Najah Vojtekova, Jana Guan, Yiqing Abba, S. El-Shafie, Ahmed TA Engineering (General). Civil engineering (General) 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. Taylor & Francis 2020-07-26 Article PeerReviewed Mohammadi, Babak and Linh, Nguyen Thi Thuy and Pham, Quoc Bao and Ahmed, Ali Najah and Vojtekova, Jana and Guan, Yiqing and Abba, S. and El-Shafie, Ahmed (2020) Adaptive neuro-fuzzy inference system coupled with shuffled frog leaping algorithm for predicting river streamflow time series. Hydrological Sciences Journal-Journal des Sciences Hydrologiques, 65 (10). pp. 1738-1751. ISSN 0262-6667, DOI https://doi.org/10.1080/02626667.2020.1758703 <https://doi.org/10.1080/02626667.2020.1758703>. 10.1080/02626667.2020.1758703
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic TA Engineering (General). Civil engineering (General)
spellingShingle TA Engineering (General). Civil engineering (General)
Mohammadi, Babak
Linh, Nguyen Thi Thuy
Pham, Quoc Bao
Ahmed, Ali Najah
Vojtekova, Jana
Guan, Yiqing
Abba, S.
El-Shafie, Ahmed
Adaptive neuro-fuzzy inference system coupled with shuffled frog leaping algorithm for predicting river streamflow time series
description 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.
format Article
author Mohammadi, Babak
Linh, Nguyen Thi Thuy
Pham, Quoc Bao
Ahmed, Ali Najah
Vojtekova, Jana
Guan, Yiqing
Abba, S.
El-Shafie, Ahmed
author_facet Mohammadi, Babak
Linh, Nguyen Thi Thuy
Pham, Quoc Bao
Ahmed, Ali Najah
Vojtekova, Jana
Guan, Yiqing
Abba, S.
El-Shafie, Ahmed
author_sort Mohammadi, Babak
title Adaptive neuro-fuzzy inference system coupled with shuffled frog leaping algorithm for predicting river streamflow time series
title_short Adaptive neuro-fuzzy inference system coupled with shuffled frog leaping algorithm for predicting river streamflow time series
title_full Adaptive neuro-fuzzy inference system coupled with shuffled frog leaping algorithm for predicting river streamflow time series
title_fullStr Adaptive neuro-fuzzy inference system coupled with shuffled frog leaping algorithm for predicting river streamflow time series
title_full_unstemmed Adaptive neuro-fuzzy inference system coupled with shuffled frog leaping algorithm for predicting river streamflow time series
title_sort adaptive neuro-fuzzy inference system coupled with shuffled frog leaping algorithm for predicting river streamflow time series
publisher Taylor & Francis
publishDate 2020
url http://eprints.um.edu.my/37621/
_version_ 1761616815427944448
score 13.211869

Similar Items