دانشکده منابع طبیعی دانشگاه تهرانJournal of Range and Watershed Managment5044-200869120160521Comparison of Neuro Fuzzy, Neural Network Artificial and Statistical Methods for Estimating Suspended Load Rivers (Case Study: Taleghan Basin Upstream)Comparison of Neuro Fuzzy, Neural Network Artificial and Statistical Methods for Estimating Suspended Load Rivers (Case Study: Taleghan Basin Upstream)65786173410.22059/jrwm.2016.61734FAAminZoratipourAssistant Professor, Department of Range and Watershed
Management, Khuzestan Ramin Agriculture and Natural Resources UniversityJournal Article20130722Abstract
Estimation of fine suspended load rivers is important in designing reserves, transition volume of<br />sediment, and estimating lake pollution. Thus, some methods are needed for determining damages<br />caused by sedimentations in environment and determining its effects on the watersheds. There are<br />many methods for estimating suspended load, one of these methods that solves the problems of<br />sediment discharge and can predict it is using Neuro fuzzy or ANFIS (Adaptive Network Fuzzy<br />Inference System), and ANN (Artificial Neural Network) methods. These make a function between<br />sediment and simultaneous discharge by use of different algorithms. The goal of this research is<br />comparing the effectiveness of Neuro fuzzy, neural network artificial and statistical methods for<br />estimating suspended load river in Glinak station of Taleghan Basin. It was found out that<br />suspended load estimations of Nero fuzzy method with MAE 1006 ton/day, and correlation<br />efficiency (R) 77%, RMSE 2621 ton/day and Nash-Sutcliff error (NS) 0.51 is better than Neural<br />Network Artificial and Statistical methods and Artificial Neural Network method rather than<br />Statistical Method are more proper. Also, contracting both neural networks artificial to fuzzy laws<br />can be illustrated better than other methods, variation of sediment Load River. One more merit of<br />this method is that it is not sensitive to few errors in early statistical data and this fact enables better<br />estimation of neural network model in comparison with statistical model. Finally, Neuro fuzzy<br />method works better as the percent of train data to test data increases.Abstract
Estimation of fine suspended load rivers is important in designing reserves, transition volume of<br />sediment, and estimating lake pollution. Thus, some methods are needed for determining damages<br />caused by sedimentations in environment and determining its effects on the watersheds. There are<br />many methods for estimating suspended load, one of these methods that solves the problems of<br />sediment discharge and can predict it is using Neuro fuzzy or ANFIS (Adaptive Network Fuzzy<br />Inference System), and ANN (Artificial Neural Network) methods. These make a function between<br />sediment and simultaneous discharge by use of different algorithms. The goal of this research is<br />comparing the effectiveness of Neuro fuzzy, neural network artificial and statistical methods for<br />estimating suspended load river in Glinak station of Taleghan Basin. It was found out that<br />suspended load estimations of Nero fuzzy method with MAE 1006 ton/day, and correlation<br />efficiency (R) 77%, RMSE 2621 ton/day and Nash-Sutcliff error (NS) 0.51 is better than Neural<br />Network Artificial and Statistical methods and Artificial Neural Network method rather than<br />Statistical Method are more proper. Also, contracting both neural networks artificial to fuzzy laws<br />can be illustrated better than other methods, variation of sediment Load River. One more merit of<br />this method is that it is not sensitive to few errors in early statistical data and this fact enables better<br />estimation of neural network model in comparison with statistical model. Finally, Neuro fuzzy<br />method works better as the percent of train data to test data increases.https://jrwm.ut.ac.ir/article_61734_bb3aba3afb5589bbc7caeb260ddf89a7.pdf