Skip to main content
SpringerLink
Log in

Forecasting Urban Water Demand Via Wavelet-Denoising and Neural Network Models. Case Study: City of Syracuse, Italy

  • Published:
Water Resources Management Aims and scope Submit manuscript

An Erratum to this article was published on 12 September 2012

Abstract

Forecasting urban water demand can be of use in the management of water utilities. For example, activities such as water-budgeting, operation and maintenance of pumps, wells, reservoirs, and mains require quantitative estimations of water resources at specified future dates. In this study, we tackle the problem of forecasting urban water demand by means of back-propagation artificial neural networks (ANNs) coupled with wavelet-denoising. In addition, non-coupled ANN and Linear Multiple Regression were used as comparison models. We considered the case of the municipality of Syracuse, Italy; for this purpose, we used a 7 year-long time series of water demand without additional predictors. Six forecasting horizons were considered, from 1 to 6 months ahead. The main objective was to implement a forecasting model that may be readily used for municipal water budgeting. An additional objective was to explore the impact of wavelet-denoising on ANN generalization. For this purpose, we measured the impact of five different wavelet filter-banks (namely, Haar and Daubechies of type db2, db3, db4, and db5) on a single neural network. Empirical results show that neural networks coupled with Haar and Daubechies’ filter-banks of type db2 and db3 outperformed all of the following: non-coupled ANN, Multiple Linear Regression and ANN models coupled with Daubechies filters of type db4 and db5. The results of this study suggest that reduced variance in the training-set (by means of denoising) may improve forecasting accuracy; on the other hand, an oversimplification of the input-matrix may deteriorate forecasting accuracy and induce network instability.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  • Adamowski J (2008) Peak daily water demand forecast modeling using artificial neural networks. J Water Resour Plan Manage 134(2):119–128

    Google Scholar 

  • Adamowski J, Chan HF (2011) A wavelet neural network conjunction model for groundwater level forecasting. J Hydrol 407(1–4):28–40

    Article  Google Scholar 

  • Adamowski J, Karapataki C (2010) Comparison of multivariate regression and artificial neural networks for peak urban water-demand forecasting: evaluation of different ANN learning algorithms. J Hydrol Eng 15:729–743

    Google Scholar 

  • Adamowski J, Sun K (2010) Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds. J Hydrol 390(1–2):85–91

    Article  Google Scholar 

  • Adamowski K, Prokoph A, Adamowski J (2009) Development of a new method of wavelet aided trend detection and estimation. Hydrol Process Spec Issue Can Geophys Union Hydrol Sect 23:2686–2696

    Google Scholar 

  • Adamowski J, Fung Chan H, Prasher SO, Ozga-Zielinski B, Sliusarieva A (2012) Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada. Water Resour Res 48:W01528. doi:10.1029/2010WR009945

    Article  Google Scholar 

  • Adar E, Neuman SP, Woolhiser DA (1988) Estimation of spatial recharge distribution using environmental isotopes and hydrochemical data: mathematical model and application to synthetic data. J Hydrol 97:251–277

    Article  Google Scholar 

  • An A, Shan N, Chan C, Cercone N, Ziarko W (1996) Discovering rules from data for water demand prediction: an enhanced rough-set approach. Eng Appl Artif Intell 9(6):645–653

    Article  Google Scholar 

  • Blatter C (1998) Wavelet: a primer. Peters Natick, Massachusetts

    Google Scholar 

  • Bougadis J, Adamowski K, Diduch R (2005) Short-term municipal water demand forecasting. Hydrol Process 19:137–148

    Google Scholar 

  • Cannas B, Fanni A, See L, Sias G (2006) Data preprocessing for river flow forecasting using neural networks: wavelet transforms and data partitioning. Phys Chem Earth 31(18):1164–1171

    Article  Google Scholar 

  • Chou CM (2011) A threshold based wavelet denoising method for hydrological data modeling. Water Resour Manag 25(7):1809–1830. doi:10.1007/s11269-011-9776-3

    Article  Google Scholar 

  • Compo GP, Torrence C (1998) A practical guide to wavelet analysis. Bull Am Meteorol Soc 79:61–78

    Article  Google Scholar 

  • Conover WJ (1980) Practical nonparametric statistics. Wiley, New York

    Google Scholar 

  • Daubechies I (1992) Ten lectures on wavelets. SIAM, Philadelphia

    Book  Google Scholar 

  • Foufoula-Georgiou E, Kumar P (1994) Wavelets in geophysics. Academic, San Diego

    Google Scholar 

  • Grubbs JW (1994) Evaluation of ground-water flow and hydrologic budget for lake Five-O, a seepage lake in Northwestern Florida. U.S. Geological Survey, WRIR 94–4145

  • Güldal V, Tongal H (2010) Comparison of recurrent neural network, adaptive neuro-fuzzy inference system and stochastic models in Egirdir Lake level forecasting. Water Resour Manag 24:105–128

    Article  Google Scholar 

  • Hagan MT, Demuth HB, Beale MH (1996) Neural network design. PWS Publishing, Boston

    Google Scholar 

  • Haykin S (1994) Neural networks, a comprehensive foundation. Macmillan College Publishing Company, New York

    Google Scholar 

  • Herrera M, Torgob L, Izquierdo J, Pérez-García R (2010) Predictive models for forecasting hourly urban water demand. J Hydrol 387(1–2):141–150

    Article  Google Scholar 

  • Holder RL (1985) Multiple regression in hydrology. Institute of hydrology, Crowmarsh Gifford

    Google Scholar 

  • Holschneider M (1995) Wavelets: an analysis tool. Oxford Mathematical Monograph, Clarendon Press

  • Issar AS, Zohar M (2009) Climate change impacts on the environment and civilization in the near East. In: Brauch HG, Spring ÚO, Grin J, Mesjasz C, Kameri-Mbote P, Behera NC, Chourou B, Krummenacher H (eds) Facing global environmental change. Springer, Berlin, pp 119–130

    Chapter  Google Scholar 

  • Jain A, Ormsbee LE (2002) Short-term water demand forecasting modeling techniques: conventional versus AI. J Am Water Works Assoc 94(7):64–72

    Google Scholar 

  • Jowitt PW, Xu C (1992) Demand forecasting for water distribution systems. Civ Eng Syst 9:105–121

    Article  Google Scholar 

  • Kisi O (2008) Stream flow forecasting using neuro-wavelet technique. Hydrol Process 22:4142–4152

    Article  Google Scholar 

  • Kisi O (2009) Neural networks and wavelet conjunction model for intermittent stream flow forecasting. J Hydrol Eng 14(8):773–782

    Article  Google Scholar 

  • Labat D (2005) Recent advances in wavelet analyses, part 1: a review of concepts. J Hydrol 314(1–4):275–288

    Article  Google Scholar 

  • Labat D (2008) Wavelet analysis of the annual discharge records of the world’s largest rivers. Adv Water Resour 31:109–117

    Article  Google Scholar 

  • Maidment DR, Miaou SP (1986) Daily water use in nine cities. Water Resour Res 22(6):845–851

    Article  Google Scholar 

  • Mallat S (1999) A wavelet tour of signal processing, 2nd edn. Academic, San Diego

    Google Scholar 

  • Meyer Y (1992) Wavelets and operators. Cambridge Studies in Advanced Mathematics, Cambridge University Press

  • Msiza IS, Nelwamondo FV, Marwala T (2007) Artificial neural networks and support vector machines for water demand time series forecasting. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, 7–10 October, Montreal, Canada, 638–643

  • Nourani V, Komasi M, Mano A (2009) A multivariate ANN-wavelet approach for rainfall-runoff modeling. Water Resour Manag 23(14):2877–2894

    Article  Google Scholar 

  • Oron G, Campos C, Gillerman L, Salgot M (1999) Wastewater treatment, renovation and reuse for agricultural irrigation in small communities. Agr Water Manag 38(3):223–234

    Article  Google Scholar 

  • Partal T, Cigizoglu HK (2008) Estimation and forecasting of the daily suspended sediment data using wavelet-neural networks. J Hydrol 358(3–4):317–331

    Article  Google Scholar 

  • Renaud O, Starck JL, Murtagh F (2005) Wavelet-Based Combined signal filtering and prediction. IEEE T Syst Man Cy B 35(6):1241–1251

    Google Scholar 

  • Rioul O, Vetterli M (1991) Wavelet and signal processing. IEEE Signal Proc Mag 8:14–38

    Article  Google Scholar 

  • Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536

    Article  Google Scholar 

  • Shirsath PB, Singh AK (2010) A comparative study of daily pan evaporation estimation using ANN, regression and climate based models. Water Resour Manag 24(8):1571–1581

    Article  Google Scholar 

  • Smith J (1988) A model of daily municipal water use of short term forecasting. Water Resour Res 24(2):201–206

    Article  Google Scholar 

  • Strang G, Nguyen T (1996) Wavelets and filter banks. Wellesley-Cambridge Press

  • Wang W, Jin J, Li Y (2009) Prediction of inflow at three gorges dam in Yangtze River with wavelet network model. Water Resour Manag 23(13):2791–2803

    Article  Google Scholar 

  • Widrow B, Lehr MA (1990) 30 years of adaptive neural networks: perceptron, madaline, and backpropagation. Proc IEEE 78(9):1415–1441

    Article  Google Scholar 

  • Zhang GP (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50:159–175

    Google Scholar 

  • Zhang GP, Patuwo EB, Hu MY (1998) Forecasting with artificial neural network: the state of the art. Int J Forecast 14:35–62

    Article  Google Scholar 

  • Zhang GP, Patuwo BE, Hu MY (2001) A simulation study of artificial neural networks for nonlinear time-series forecasting. Comput Oper Res 28(4):381–396

    Article  Google Scholar 

  • Zhou H, Peng Y, Liang G (2007) The research of monthly discharge predictor-corrector model based on wavelet decomposition. Water Resour Manag 22(2):217–227

    Article  Google Scholar 

Download references

Acknowledgments

This study was supported by the Norman Zavalkoff Foundation whose help is greatly appreciated. This study was also partially funded by a NSERC Discovery Grant held by Jan Adamowski, and by the IWRM-SMART project of The Federal Ministry of Education and Research, Germany, and The Ministry of Science and Technology (MOST) of the State of Israel. The authors would also like to thank the anonymous reviewers for their valuable comments.

Author information

Authors and Affiliations

  1. Albert Katz International School for Desert Studies, The Jacob Blaustein Institutes for Desert Research, Ben-Gurion University of the Negev, Beersheba, Israel

    Salvatore Campisi-Pinto

  2. Department of Bioresource Engineering, Faculty of Agricultural and Environmental Sciences, McGill University, Montreal, Canada

    Jan Adamowski

  3. The Department of Industrial Engineering and Management, Ben-Gurion University of the Negev, Beer Sheva, 84105, Israel

    Gideon Oron

Authors
  1. Salvatore Campisi-Pinto
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jan Adamowski
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Gideon Oron
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jan Adamowski.

ANNEX A

ANNEX A

Table 4 Model performances in multi ahead forecasting (from 2 to 6 months ahead)
Full size table

Rights and permissions

Reprints and permissions

About this article

Cite this article

Campisi-Pinto, S., Adamowski, J. & Oron, G. Forecasting Urban Water Demand Via Wavelet-Denoising and Neural Network Models. Case Study: City of Syracuse, Italy. Water Resour Manage 26, 3539–3558 (2012). https://doi.org/10.1007/s11269-012-0089-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11269-012-0089-y

Keywords

Search

Navigation