Monitoring event-based suspended sediment concentration by artificial neural network models

This paper is concerned with monitoring the hourly event-based river suspended sediment concentration (SSC) due to storms in Jiasian diversion weir in southern Taiwan. The weir is built for supplying 0.3 million tons of water per day averagely for civil and industrial use. Information of suspended sediments fluxes of rivers is crucial for monitoring the quality of water. The issue of water quality is of particular importance to Jiasian area where there are high population densities and intensive agricultural activities. Therefore, this study explores the potential of using artificial neural networks (ANNs) for modeling the event-based SSC for continuous monitoring of the river water quality. The data collected include the hourly water discharge, turbidity and SSC during the storm events. The feed forward backpropagation network (BP), generalized regression neural network (GRNN), and classical regression were employed to test their performances. From the statistical evaluation, it has been found that the performance of BP was slightly better than GRNN model. In addition, the classical regression performance was inferior to ANNs. Statistically, it appeared that both BP (r2=0.930) and GRNN (r2=0.927) models fit well for estimating the event-based SSC in the Jiasian diversion weir. The weir SSC estimation using a single input data with the neural networks showed the dominance of the turbidity variable over water discharge. Furthermore, using the the ANN models are more reliable than classical regression method for estimating the SSC in the area studied herein.

[1]  L. M. Svendsen,et al.  Bank erosion as a source of sediment and phosphorus delivery to small Danish streams , 2000 .

[2]  R. Eads,et al.  Turbidity-controlled suspended sediment sampling , 1996 .

[3]  Hilmi Berk Celikoglu,et al.  Public transportation trip flow modeling with generalized regression neural networks , 2007, Adv. Eng. Softw..

[4]  R. S. Govindaraju,et al.  Artificial Neural Networks in Hydrology , 2010 .

[5]  Narendra Singh Raghuwanshi,et al.  Estimating Evapotranspiration using Artificial Neural Network , 2002 .

[6]  A. Sarangi,et al.  Comparison of Artificial Neural Network and regression models for sediment loss prediction from Banha watershed in India , 2005 .

[7]  J. Poesen,et al.  Spatial variation of suspended sediment concentrations in a tropical Andean river system: The Paute River, southern Ecuador , 2007 .

[8]  A. Collins,et al.  Assessing the likelihood of catchments across England and Wales meeting ‘good ecological status’ due to sediment contributions from agricultural sources , 2008 .

[9]  M. Firat,et al.  Comparison of Artificial Intelligence Techniques for river flow forecasting , 2008 .

[10]  G. Sahoo,et al.  Use of neural network to predict flash flood and attendant water qualities of a mountainous stream on Oahu, Hawaii , 2006 .

[11]  S. Galassi,et al.  Assessment of river Po sediment quality by micropollutant analysis. , 2002, Water research.

[12]  Demetris Koutsoyiannis,et al.  Discussion of “Generalized regression neural networks for evapotranspiration modelling” , 2007 .

[13]  Roland K. Price,et al.  Data-driven modelling in the context of sediment transport , 2005 .

[14]  Xixi Lu,et al.  Spatial variability and temporal change of water discharge and sediment flux in the Lower Jinsha tributary: impact of environmental changes , 2005 .

[15]  R. K. Rai,et al.  Event-based Sediment Yield Modeling using Artificial Neural Network , 2008 .

[16]  Surendra Kumar Mishra,et al.  ANN-based sediment yield models for Vamsadhara river basin (India) , 2005 .

[17]  Richard Labib,et al.  Performance of Neural Networks in Daily Streamflow Forecasting , 2002 .

[18]  Hikmet Kerem Cigizoglu,et al.  Rainfall-Runoff Modelling Using Three Neural Network Methods , 2004, ICAISC.

[19]  D. W. Scott,et al.  Multivariate Density Estimation, Theory, Practice and Visualization , 1992 .

[20]  Ourania Tzoraki,et al.  A generalized framework for modeling the hydrologic and biogeochemical response of a Mediterranean temporary river basin , 2007 .

[21]  N. Smith,et al.  Sediment production and transport in a proglacial stream , 2008 .

[22]  K. P. Sudheer,et al.  Estimating Actual Evapotranspiration from Limited Climatic Data Using Neural Computing Technique , 2003 .

[23]  M. Macklin,et al.  Speciation of heavy metals on suspended sediment under high flow conditions in the River Aire, West Yorkshire, UK , 1998 .

[24]  O. Ks.  Multi-layer perceptrons with Levenberg-Marquardt training algorithm for suspended sediment concentration prediction and estimation , 2004 .

[25]  S. Anthony,et al.  Predicting the Impact of Projected Change in Agriculture by 2015 on Annual Mean Fluvial Suspended Sediment Concentrations Across England and Wales , 2007 .

[26]  Özgür Kişi,et al.  Multi-layer perceptrons with Levenberg-Marquardt training algorithm for suspended sediment concentration prediction and estimation / Prévision et estimation de la concentration en matières en suspension avec des perceptrons multi-couches et l’algorithme d’apprentissage de Levenberg-Marquardt , 2004 .

[27]  R. Prego,et al.  The contribution of total suspended solids to the Bay of Biscay by Cantabrian Rivers (northern coast of the Iberian Peninsula) , 2008 .

[28]  Scott D. Peckham,et al.  Modeling the temporal variability in the flux of sediment from ungauged river basins , 2003 .

[29]  R. Gordon,et al.  Resuspension of sediment-associated Escherichia coli in a natural stream. , 2005, Journal of environmental quality.

[30]  John F. Orwin,et al.  An inexpensive turbidimeter for monitoring suspended sediment , 2005 .

[31]  Hikmet Kerem Cigizoglu,et al.  Generalized regression neural network in modelling river sediment yield , 2006, Adv. Eng. Softw..

[32]  Xixi Lu,et al.  Suspended sediment flux modeling with artificial neural network: An example of the Longchuanjiang River in the Upper Yangtze Catchment, China , 2007 .

[33]  B. Hallet,et al.  Rates of erosion and sediment evacuation by glaciers: A review of field data and their implications , 1996 .

[34]  Y. Chtioui,et al.  A generalized regression neural network and its application for leaf wetness prediction to forecast plant disease , 1999 .

[35]  O. Kisi,et al.  A genetic programming approach to suspended sediment modelling , 2008 .

[36]  Alessandro Bigi,et al.  A new indirect method to estimate suspended sediment concentration in a river monitoring programme , 2005 .

[37]  K. Richards,et al.  Links between proglacial stream suspended sediment dynamics, glacier hydrology and glacier motion at Midtdalsbreen, Norway , 1996 .

[38]  R. C. Ferrier,et al.  Catchment microbial dynamics: the emergence of a research agenda , 2007 .

[39]  D. Absalon,et al.  Changes in water quality and runoff in the Upper Oder River Basin , 2007 .

[40]  A. Pagliarani,et al.  SW—Soil and Water: Monitoring Water Flow, Turbidity and Suspended Sediment Load, from an Apennine Catchment Basin, Italy , 2002 .

[41]  Johnson U. Kitheka,et al.  River discharge, sediment transport and exchange in the Tana Estuary, Kenya , 2005 .