home icon user icon
Welcome to International Network for Natural Sciences | INNS Pub.
Home My Account
Submit Manuscript
double_slash
breadcumb_bg

Modeling sediment yield using artificial neural network and multiple linear regression methods

Paper Details

Research Paper 01/09/2013
Views (292) Download (2)
current_issue_feature_image
publication_file

Modeling sediment yield using artificial neural network and multiple linear regression methods

Lida Eisazadeh, Reza Sokouti, Mehdi Homaee, Ebrahim Pazira
Int. J. Biosci.3( 9), 116-122, September 2013.
Certificate: IJB 2013 [Generate Certificate]
Key: Artificial neural networkRegressionSediment estimationSediment-retention reservoirs

Abstract

Estimating sediment yield in upstream sub basins of reservoirs is an important issue for designing and operation of water resources structures. In classical methods of predicting sediment yield (e. g. regression models) internal uncertainties are not explicitly taken into consideration. However this model cannot improve understanding the internal relationships between the data extracted and cannot determines the impact of each factor of sediment yield. The use of artificial neural networks modeling for prediction and forecasting variables in sedimentation are easier, cheaper and they begin to solve nonlinear problems. In this study, 25 sub basin of reservoir in West Azerbaijan province, Iran, were selected for estimating sediment yield by using multiple linear regression (MLR) and artificial neural network (ANN) methods. Therefore, 160 data sets of sediment yield have been used in selected sub basins of reservoirs. In ANN method, different combinations of inputs and different kinds of functions were designed with the best model by error back propagation algorithm. Also, in the MLR method, a model established by using different parameters of climatic and geomorphological factors. Some statistics including RMSE and R2 were used to evaluate the performance of applied models. The results indicated the proposed ANN model could well predict the sediment yield with R2 = 0. 86 and RMSE= 0.09 in comparison to the MLR model which it’s R2 and RMSE are 0.64 and 1.41 respectively. In particular, the ANN model had the capability of discovering non-linear relationships of sedimentation using geomorphologic parameters with reasonable precision.

VIEWS 3
Cover PDF

Agrowal A, Singh RD, Mishra S K, Bhung PK. 2006. ANN based sediment yield models for Vamsadhara River Basin (India). Water SA 31, 95-100.

Alborzi M. 2010. Introduction of neural networks. Sharif university press. 207 p.

Cigizoglu HK, Alp M. 2007. Generalized regression neural network in modeling river sediment yield. Advance in engineering software 37, 63-68. http://dx.doi.org/10.1080/10286600500126256

Cigizoglu HK, Kisi O. 2006. Methods to improve the neural network performance in suspended sediment estimation”, J. of Hydrology 317, 221-238. http://dx.doi.org/10.1016/j.jhydrol.2005.05.019

Kerem H. 2006. Generalized regression neural network in modeling river sediment yield. Advances in Engineering Software 37, 63–68.

Mirbagheri SA, Rajaee T. 2005. Using artificial neural network to estimate bed load sediment in Zohre River. Proceeding of first international congress of civil engineering. Sharif University, Tehran. (In Persian).

Morgan RPC. 1996. Soil erosion and conservation. Second Edition. 198 p.

Nagy HM, Watanabe K, Hirano M. 2002. Prediction of sediment load concentration in rivers using artificial neural network model. Journal of Hydraulic Engineering ASCE 128(6), 588–595. http://dx.doi.org/10.1061/(ASCE)0733-9429(2002)128:6(588)

Sarangi A, Bhattacharya AK. 2005. Comparison of artificial neural network and regression models for sediment loss prediction from Banha watershed in India. Agricultural Water Management 78, 195-208. http://dx.doi.org/10.1016/j.agwat.2005.02.001

Tayfur G, Guldal V. 2006. Artificial neural networks for estimating daily total suspended sediment in natural streams, Nordic Hydrology 37, 69-79.

Youssefvand F, Ghelmaei S H, Ghamarnia H, Zia tabarahmadi MK. 2005. The effect of time measuring classification of suspended sediment of rivers. 5th Hydraulic conference. Kerman, Iran. (In Persian).

Zhu YM, Lu XX, Zhou Y. 2007. Suspended sediment flux modeling with artificial neural network: An example of the Longchuanjiang River in the Upper Yangtze Catchment, China. Geomorphology 84, 111-125.

Submit Manuscript