Estimation of Discharge in Rivers using ANN Modeled Rating Curves
Tóm tắt
Rating curves, commonly used for estimation of discharge in a river are usually steady-flow rating curves, in which discharge is expressed as a function of stage only. However, these rating curves may be inadequate due to a number of factors like backwater effect, changes in cross-section from scouring or silting, rapidly changing discharge etc. Problems with variable backwater and unsteady flow are usually dealt by including additional parameters like water surface slope in the stage–discharge relation. But these approaches have limitations due to absence of other parameters governing flow conditions in the model. In these cases, artificial neural network (ANN) can be used effectively as an alternative. Models with multiple input variables can be developed for prediction of discharge with much more accuracy. In this work, a number of ANN models have been developed for estimation of discharge. Stage and discharge data from a river reach with a bridge crossing were used for training, validation and simulation of the ANN models. Results show that the neural networks are capable of predicting the discharges under varying flow conditions. Loops in rating curves and backwater effect are estimated quite accurately by multiple-input ANN models.
Tài liệu tham khảo
S.K. Jain, D. Chalisgaonkar, Setting up stage–discharge relations using ANN. J. Hydrol. Eng. 5(4), 428–433 (2000)
ASCE Task Committee, Artificial neural network in hydrology. J. Hydrol. Eng. 5(2), 124–144 (2000)
C.W. Dawson, R. Wilby, An artificial neural network approach to rainfall-runoff modeling. Hydrol. Sci. J. 43(1), 47–66 (1998)
A.W. Minns, M.J. Hall, Artificial neural networks as rainfall runoff models. Hydrol. Sci. J. 41(3), 399–418 (1996)
H. K. Cigizoglu, Estimation and forecasting of daily suspended sediment data by multi-layer perceptrons. Adv. Water Resour. 27, 185–195 (2004)
Tsai et al, Back-propagation neural network in tidal level forecasting. J. Waterw., Port, Coast., Ocean Eng. (1999)
Y. Dibike, D.P. Solomatine, M.B. Abbott, On the encapsulation of numerical-hydraulic models in artificial neural network. J. Hydraul. Res. 37(2), 147–161 (1999)
A.R. Schmidt, M.H. Garcia, Theoretical examination of historical shifts and adjustments to stage–discharge rating curves, in Proceedings of EWRI World Water and Environmental Congress., Philadelphia (2001)
B. Bhattacharya, D.P. Solomantine, Application of artificial neural network in stage-discharge relationship, in Proceedings of the 4-th International Conference on Hydroinformatics, Iowa City (2000)
B. Bhattacharya, D.P. Solomatine, Neural networks and M5 model trees in modeling water level–discharge relationship. Neurocomputing 63, 381–396 (2005)
G.B. Sahoo, C. Ray, Flow forecasting for a Hawaii stream using rating curves and neural networks. J. Hydrol. 317, 63–80 (2006)
HECRAS User’s Manual, Version 4, March 2008
M.T. Hagan, H.P. Demuth, M. Beale, Neural Network Design (PWS Publishing, Boston, 1996)