Artificial neural networks for estimating daily total suspended sediment in natural streams

Estimates of sediment loads in natural streams are required for a wide spectrum of water resources engineering problems from optimal reservoir design to water quality in lakes. Suspended sediment constitutes 75–95% of the total load. The nonlinear problem of suspended sediment estimation requires a nonlinear model. An artificial neural network (ANN) model has been developed to predict daily total suspended sediment (TSS) in rivers. The model is constructed as a three-layer feedforward network using the back-propagation algorithm as a training tool. The model predicts TSS rates using precipitation (P) data as input. For network training and testing 240 sets of data sets were used. The model successfully predicted daily TSS loads using the present and past 4 days precipitation data in the input vector with R 2 =0.91 and MAE =34.22 mg/L. The performance of the model was also tested against the most recently developed non-linear black box model based upon two-dimensional unit sediment graph theory (2D-USGT). The comparison of results revealed that the ANN has a significantly better performance than the 2D-USGT. Investigation results revealed that the ANN model requires a period of more than 75 d of measured P-TSS data for training the model for satisfactory TSS estimation. The statistical parameter range ( x min − x max ) plays a major role for optimal partitioning of data into training and testing sets. Both sets should have comparable values for the range parameter.

[1]  O. Rendon‐Herrero.  unit sediment graph , 1978 .

[2]  Veysel Güldal,et al.  2D Unit Sediment Graph Theory , 2001 .

[3]  G. Tayfur.  Applicability of Sediment Transport Capacity Models for Nonsteady State Erosion from Steep Slopes , 2002 .

[4]  J. Amorocho,et al.  The nonlinear prediction problem in the study of the runoff cycle , 1967 .

[5]  Hikmet Kerem Ciğizoğlu,et al.  Suspended Sediment Estimation and Forecasting using Artificial Neural Networks , 2002 .

[6]  Gokmen Tayfur,et al.  Modeling Two-Dimensional Erosion Process over Infiltrating Surfaces , 2001 .

[7]  V. Singh,et al.  Case Study: Finite Element Method and Artificial Neural Network Models for Flow through Jeziorsko Earthfill Dam in Poland , 2005 .

[8]  J. Williams.  A sediment graph model based on an instantaneous unit sediment graph , 1978 .

[9]  Jun Xia,et al.  A non-linear perturbation model considering catchment wetness and its application in river flow forecasting , 1997 .

[10]  R. Müftüoğlu,et al.  Monthly runoff generation by non-linear models , 1991 .

[11]  R Govindaraju,et al.  ARTIFICIAL NEURAL NETWORKS IN HYDROLOGY: II, HYDROLOGIC APPLICATIONS , 2000 .

[12]  N. Null.  Artificial Neural Networks in Hydrology. I: Preliminary Concepts , 2000 .

[13]  R.Ferruh Müftüoğlu.  New models for nonlinear catchment analysis , 1984 .

[14]  Yee-Chung Jin,et al.  Modeling Nonuniform Suspended Sediment Transport in Alluvial Rivers , 2002 .

[15]  Christian W. Dawson,et al.  An artificial neural network approach to rainfall-runoff modelling , 1998 .

[16]  Ashu Jain,et al.  Comparative Analysis of Event-Based Rainfall-Runoff Modeling Techniques—Deterministic, Statistical, and Artificial Neural Networks , 2003 .