Comparison of Neuro Fuzzy, Neural Network Artificial and Statistical Methods for Estimating Suspended Load Rivers (Case Study: Taleghan Basin Upstream)

Document Type : Research Paper

Author

Assistant Professor, Department of Range and Watershed Management, Khuzestan Ramin Agriculture and Natural Resources University

Abstract

Abstract
Estimation of fine suspended load rivers is important in designing reserves, transition volume of
sediment, and estimating lake pollution. Thus, some methods are needed for determining damages
caused by sedimentations in environment and determining its effects on the watersheds. There are
many methods for estimating suspended load, one of these methods that solves the problems of
sediment discharge and can predict it is using Neuro fuzzy or ANFIS (Adaptive Network Fuzzy
Inference System), and ANN (Artificial Neural Network) methods. These make a function between
sediment and simultaneous discharge by use of different algorithms. The goal of this research is
comparing the effectiveness of Neuro fuzzy, neural network artificial and statistical methods for
estimating suspended load river in Glinak station of Taleghan Basin. It was found out that
suspended load estimations of Nero fuzzy method with MAE 1006 ton/day, and correlation
efficiency (R) 77%, RMSE 2621 ton/day and Nash-Sutcliff error (NS) 0.51 is better than Neural
Network Artificial and Statistical methods and Artificial Neural Network method rather than
Statistical Method are more proper. Also, contracting both neural networks artificial to fuzzy laws
can be illustrated better than other methods, variation of sediment Load River. One more merit of
this method is that it is not sensitive to few errors in early statistical data and this fact enables better
estimation of neural network model in comparison with statistical model. Finally, Neuro fuzzy
method works better as the percent of train data to test data increases.

Keywords


Volume 69, Issue 1
June 2016
Pages 65-78
  • Receive Date: 22 July 2013
  • Revise Date: 16 November 2014
  • Accept Date: 12 December 2014
  • First Publish Date: 21 May 2016