Document Type : Research Paper


1 Assist. Professor, Soil Conservation and Watershed Management Research Department, Markazi Agricultural and Natural Resources Research and Education Center, AREEO,, Arak, Iran

2 Assist. Professor, Department of Water Engineering, Faculty of Agriculture, University of Arak, Arak, Iran

3 Ph.D. Scholar, Department of Watershed Management, Faculty of Agriculture, Tarbiat Modares University, Tehran, Iran


Estimation of sediment load in rivers is one of the most important and applicable issues in studies and design of river and water engineering projects. Therefore, identification and suggestion of suitable methods for estimating suspended sediment load should be done based on relevant research. These methods include artificial neural network models, neurophysics, sedimentation rate curve as well as multivariate regression model. In this study, the efficiency of these methods was investigated in predicting discharge rate of suspended sediments of Gharachai River watershed. Daily time series data of measured flow discharge and sedimentation of bridge station of Gharachai River were used. The statistical period used in this model was two years (2016-2017). Independent variables used to enter the network include runoff and suspended load at the Gharachai River Doab Bridge station. The dependent variable, which is the network output, was the suspended load. After modeling with each compound and calculating RMSE and R2 values, the best combination was selected. The results showed that the neurophasic method based on discharge and sediment inputs and artificial neural network models based on discharge inputs were more accurate than multivariate regression and sedimentation rate curve. For values ​​higher the long-run mean of the statistical series, the values ​​simulated by the ANN model and for values less the mean and annual sediment load were also closer to the observed values. While for maximum values, no significant difference was found between ANN models, neurophysics, and linear regression.


Main Subjects

Alp M. and Cigizoglu H. K. (2007). Suspended sediment load simulation by two artificial neural network methods using hydro meteorological data. Environ. Model. Software, 22, 2-13.
Bhattacharya B., Price R. K. and Solomatine D. P. (2007). Machine Learning Approach to Modeling Sediment Transport. J. Hydraul. Eng., 133, 440-450.
Cobaner M., Unal B. and Kisi O. (2009). Suspended sediment concentration estimation by an adaptive neuro-fuzzy and neural network approaches using hydro meteorological data. J. Hydrol., 367, 52–61.
Duan W. L., He B., Takara K., Luo P. P., Nover D. and Hu M. C. (2015). Modeling suspended sediment sources and transport in the Ishikari River basin, Japan, using SPARROW. Hydraul. Earth Sys. Sci., 19, 1293-1306.
Eshghi P., Farzadmehr J., Dastorani M. T. and Arabasadi Z. (2016). The Effectiveness of intelligent model in estimating the river suspended sediments (case study: Babaaman basin, Northern khorasan). J. Watershed Manage. Res., 7(14), 88-95 [In Persian].
Heng S. and Suetsugi T. (2013). Using artificial neural network to estimate sediment load in ungauged catchments of the Tonle Sap River Basin, Cambodia. J. Water Resour. Protect., 5, 111-123.
Jain S. K. )2001(. Development of integrated sediment rating curves using ANNs. J. Hydraul. Eng. 127(1), 30–37.
Kakaei Lafdani E., Moghaddam Nia A. and Ahmadi A. (2013). Daily suspended sediment load prediction using artificial neural networks and support vector machines. J.  Hydrol., 478, 50-62 [In Persian].
Kia E., Emadi A. R. and Fazlola R. (2013). Investigation and evaluation of artificial neural networks in Babolroud River suspended load estimation. J. Civil Eng. Urban., 3(4), 183-190 [In Persian].
Kisi O. )2005(. Suspended sediment estimation using neuro-fuzzy and neural network approaches. Hydrol. Sci. J. (des Sci. Hydrol.), 50(4), 683-696
Kisi O., Haktanir T., Ardiclioglu M., Ozturk O., Yalcin E. and Uludag S. )2009(. Adaptive neuro-fuzzy computing technique for suspended sediment estimation. Adv. Eng. Software 40, 438–444.
Kumar Goyal M. (2014). Modeling of sediment yield prediction using M5 model tree algorithm and wavelet regression. J. Water Resour. Manage., 28, 1991-2003.
Lohani A. K., Goel N. K. and Bhatia K. K. S. )2007(. Deriving stage–discharge–sediment concentration relationships using fuzzy logic. Hydrol. Sci. J., 52(4), 793–807.
Nagy H. M., Watanabe K. and Hirano M. )2002(. Prediction of load concentration in rivers using artificial neural network model. J. Hydraul. Eng., 128(6), 588–595.
Rajaee T., Mirbagheri S. A., Nourani V. and Alikhani A. (2010). Prediction of daily suspended sediment load using wavelet and neuro fuzzy combined model. Int. J. Environ. Sci. Tech., 7(1), 93-110 [In Persian].
Sattari M. T., Rezazadeh Judi A., Safdari F. and Ghahremanzadeh F. (2016). Evaluation of the performance of M-tree modeling methods and regression vector support in river sediment modeling. J. Conserv. Soil Water Resour., 2(4), 109-123 [In Persian].
Senthil Kumar A. R., Ojha C. S., Manish Kumar Goyal P., Singh R. D. and Swamee P. K. )2012(. Modeling of suspended sediment concentration at Kasol in India using ANN, fuzzy logic and decision tree algorithms. A.S.C.E., 17, 394-404.
Zhu Y. M., Lu X. X. and Zhou Y. )2007(. Suspended sediment flux modeling with artificial neural network: an example of the Longchuanjiang River in the Upper Yangtze Catchment, China. Geomor., 84, 111–125.