EVALUATION OF ARTIFICIAL NEURAL NETWORK TECHNIQUES FOR MUNICIPAL WATER CONSUMPTION MODELING
作者： Mahmut Firat , Mehmet Ali Yurdusev , Mustafa Erkan Turan
DOI: 10.1007/S11269-008-9291-3
关键词:
摘要: Various Artificial Neural Network techniques such as Generalized Regression Networks (GRNN), Feed Forward (FFNN) and Radial Basis (RBNN) have been evaluated based on their performance in forecasting monthly water consumptions from several socio-economic climatic factors, which affect use. The data set including total 108 records is divided into two subsets, training testing. models consisting of the combination independent variables are constructed best fit input structure investigated. ANN testing stages compared with observed consumption values to identify model. For this purpose, some criteria Normalized Root Mean Square Error (NRMSE), efficiency (E) correlation coefficient (CORR) calculated for all models. also trained tested by Multiple Linear (MLR). results indicated that GRNN outperforms other methods modeling consumptions.
springer.com
cabdirect.org
sci-hub.se 参考文章(24)
Hikmet Kerem Cigizoglu, Generalized regression neural network in monthly flow forecasting Civil Engineering and Environmental Systems. ,vol. 22, pp. 71- 81 ,(2005) , 10.1080/10286600500126256
Gwo-Fong Lin, Lu-Hsien Chen, A non-linear rainfall-runoff model using radial basis function network Journal of Hydrology. ,vol. 289, pp. 1- 8 ,(2004) , 10.1016/J.JHYDROL.2003.10.015
Jozef Komorník, Magda Komorníková, Radko Mesiar, Danuša Szökeová, Ján Szolgay, Comparison of forecasting performance of nonlinear models of hydrological time series Physics and Chemistry of The Earth. ,vol. 31, pp. 1127- 1145 ,(2006) , 10.1016/J.PCE.2006.05.006
A. R. Senthil Kumar, K. P. Sudheer, S. K. Jain, P. K. Agarwal, Rainfall‐runoff modelling using artificial neural networks: comparison of network types Hydrological Processes. ,vol. 19, pp. 1277- 1291 ,(2005) , 10.1002/HYP.5581
John Bougadis, Kaz Adamowski, Roman Diduch, Short‐term municipal water demand forecasting Hydrological Processes. ,vol. 19, pp. 137- 148 ,(2005) , 10.1002/HYP.5763
Dae-Il Jeong, Young-Oh Kim, Rainfall-runoff models using artificial neural networks for ensemble streamflow prediction Hydrological Processes. ,vol. 19, pp. 3819- 3835 ,(2005) , 10.1002/HYP.5983
S.L. Zhou, T.A. McMahon, A. Walton, J. Lewis, Forecasting daily urban water demand: a case study of Melbourne Journal of Hydrology. ,vol. 236, pp. 153- 164 ,(2000) , 10.1016/S0022-1694(00)00287-0
Inmaculada Pulido-Calvo, Pilar Montesinos, José Roldán, Francisco Ruiz-Navarro, Linear regressions and neural approaches to water demand forecasting in irrigation districts with telemetry systems Biosystems Engineering. ,vol. 97, pp. 283- 293 ,(2007) , 10.1016/J.BIOSYSTEMSENG.2007.03.003
Hikmet Kerem Cigizoglu, Murat Alp, Generalized regression neural network in modelling river sediment yield Advances in Engineering Software. ,vol. 37, pp. 63- 68 ,(2006) , 10.1016/J.ADVENGSOFT.2005.05.002
J.E. Nash, J.V. Sutcliffe, River flow forecasting through conceptual models part I — A discussion of principles☆ Journal of Hydrology. ,vol. 10, pp. 282- 290 ,(1970) , 10.1016/0022-1694(70)90255-6