Comparison of multivariate regression and artificial neural networks for peak urban water-demand forecasting: Evaluation of different ANN learning algorithms

Journal of Hydrologic Engineering

Volumn 15, Issue 10, 2010, Pages 729-743

  Adamowski, Jan ^a   Karapataki, Christina ^b  

^a MCGILL UNIVERSITY   (Canada)

^b UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Artificial intelligence; Artificial neural networks; Forecasting; Municipal water; Regression analysis; Water demand; Water resource management

Indexed keywords

ACCURATE PREDICTION; ARTIFICIAL NEURAL NETWORK; CONJUGATE GRADIENT; DEMAND DATA; DEMAND FORECAST; DEMAND FORECASTING; DEMAND REDUCTION; LEVENBERG-MARQUARDT; LEVENBERG-MARQUARDT ARTIFICIAL NEURAL NETWORKS; METEOROLOGICAL VARIABLES; MULTI LAYER PERCEPTRON; MULTIPLE LINEAR REGRESSION MODELS; MULTIPLE LINEAR REGRESSIONS; MULTIVARIATE REGRESSION; MUNICIPAL WATER; RELATIVE PERFORMANCE; RESILIENT BACKPROPAGATION; URBAN WATERS; WATER CRISIS; WATER DEMAND; WATER RESOURCE MANAGEMENT; WATER SOURCE; WATER USE;

ARTIFICIAL INTELLIGENCE; CONJUGATE GRADIENT METHOD; LEARNING ALGORITHMS; MULTILAYER NEURAL NETWORKS; RAIN; RESOURCE ALLOCATION; WATER CONSERVATION; WATER MANAGEMENT; WATER SUPPLY; WATER SUPPLY SYSTEMS; WEATHER FORECASTING;

LINEAR REGRESSION;

ALGORITHM; ARTIFICIAL INTELLIGENCE; ARTIFICIAL NEURAL NETWORK; DROUGHT; FORECASTING METHOD; MULTIVARIATE ANALYSIS; REGRESSION ANALYSIS; URBAN AREA; WATER MANAGEMENT; WATER SUPPLY;

CYPRUS;

EID: 77956838672     PISSN: 10840699     EISSN: None     Source Type: Journal    
DOI: 10.1061/(ASCE)HE.1943-5584.0000245     Document Type: Article

References (49)

1. Adamowski J.F. Peak daily water demand forecast modeling using artificial neural networks. J. Water Resour. Plann. Manage. 2008, 134(2):119-128. JWRMD5, 0733-9496, 10.1061/(ASCE)0733-9496(2008)134:2(119)
2. Anderson R. Miller T. Washburn M. Water savings from lawn watering restrictions during a drought year in Fort Collins, Colorado. Water Resour. Bull. 1980, 16(4):642-645. WARBAQ, 0043-1370
3. Aqil M. Kita I. Yano A. Nishiyama S. Neural networks for real time catchment flow modeling and prediction. Water Resour. Manage. 2007, 21(10):1781-1796. WRMAEJ, 0920-4741, 10.1007/s11269-006-9127-y
4. Artemis C. Country report-Cyprus. Conf. of the Water Directors of the Euro-Mediterranean and Southeastern European Countries 2006, Dept. of Water Development, Nicosia, Cyprus.
5. Beale E. A derivation of conjugate gradients: Numerical methods for nonlinear optimization 1972, Academic, San Diego.
6. Bougadis J. Adamowski K. Diduch R. Short-term municipal water demand forecasting. Hydrolog. Process. 2005, 19(1):137-148. HYPRE3, 0885-6087, 10.1002/hyp.5763
7. Chen X.Y. Li P. Yuan Y. Shi X. Forecast of water using improved Chebyshev neural network. Journal of Petrochemical Universities 2005, 18(1):70-72.
8. Cigizoglu H.K. Kisi O. Flow prediction by three back propagation techniques using k-fold partitioning of neural network training data. Nord. Hydrol. 2005, 36(1):49-64. NOHYBB, 0029-1277
9. Dawson C.W. Harpham C. Wilby R.L. Chen Y. Evaluation of artificial neural network techniques for flow forecasting in the River Yangtze, China. Hydrology Earth Syst. Sci. 2002, 6(4):619-626. 1027-5606, 10.5194/hess-6-619-2002
10. Dawson C.W. Wilby R.L. A comparison of artificial neural networks used for river flow forecasting. Hydrology Earth Syst. Sci. 1999, 3(4):529-540. 1027-5606, 10.5194/hess-3-529-1999
11. Day D. Howe C. Forecasting peak demand-What do we need to know?. Water Sci. Technol.: Water Supply 2003, 3(3):177-184. WSTWBM, 1606-9749
12. Fernando D.A. K. Jayawardena A.W. Runoff forecasting using RBF networks with OLS algorithm. J. Hydrol. Eng. 1998, 3(3):203-209. JHYEFF, 1084-0699, 10.1061/(ASCE)1084-0699(1998)3:3(203)
13. Gabriel M. Drought-hit Cyprus starts emergency water rations. 2008, (Internet). New York; Reuters, Mar. 24.
14. Ghiassi G. Zimbra D.K. Saidane H. Urban water demand forecasting with a dynamic artificial neural network model. J. Water Resour. Plann. Manage. 2008, 134(2):138-146. JWRMD5, 0733-9496, 10.1061/(ASCE)0733-9496(2008)134:2(138)
15. Gutzler D.S. Nims J.S. Interannual variability of water demand and summer climate in Albuquerque, New Mexico. J. Appl. Meteorol. 2005, 44(12):1777-1787. JAMOAX, 0021-8952, 10.1175/JAM2298.1
16. Heller M. Singh Thind H. Forecasting with cascade correlation: An application to potable water demand. Artificial Neural Networks in Engineering-Proceedings 1994, 4:1155-1160.
17. Howe C. Linaweaver F. The impact of price on residential water demand and its relation to systems design. Water Resour. Res. 1967, 3(1):13-32. WRERAQ, 0043-1397, 10.1029/WR003i001p00013
18. Huang G.R. Hu H. Tian F. Flood level forecast model for tidal channel based on the radial basis function artificial neural network. Advances in Water Science 2003, 14(2):158-162.
19. Hughes T. Peak period design standards for small western US water supply. Water Resour. Bull. 1980, 16(4):661-667. WARBAQ, 0043-1370
20. Jain A. Ormsbee L. Short-term water demand forecast modeling techniques-Conventional methods versus AI. J. Am. Water Works Assoc. 2002, 94(7):64-72. JAWWA5, 0003-150X
21. Jain A. Varshney A. Joshi U. Short-term water demand forecast modeling at IIT Kanpar using artificial neural networks. Water Resour. Manage. 2001, 15(5):299-321. WRMAEJ, 0920-4741, 10.1023/A:1014415503476
22. Jayawardena A.W. Fernando D. A.W. Zhou M.C. Comparison of multilayer perceptron and radial basis function networks as tools for flood forecasting. ProcDestructive Water: Water Caused Natural Disasters Their Abatement and Control 1997, 173-181. and IAHS, No. 239
23. Jayawardena A.W. Achela C. Fernando K. Use of radial basis function type artificial neural networks for runoff simulation. Comput. Aided Civ. Infrastruct. Eng. 1998, 13(2):91-99. CCIEFR, 1093-9687, 10.1111/0885-9507.00089
24. Karul C. Soyupak S. Cilesiz A.F. Akbay N. Germen E. Case studies on the use of neural networks in eutrophication modeling. Ecol. Modell. 2000, 134:145-152. ECMODT, 0304-3800, 10.1016/S0304-3800(00)00360-4,
25. Kişi O. Streamflow forecasting using different artificial neural network algorithms. J. Hydrol. Eng. 2007, 12(5):532-539. JHYEFF, 1084-0699, 10.1061/(ASCE)1084-0699(2007)12:5(532)
26. Lange M. Climate change: Impacts and adaptation strategies in the Eastern Mediterranean. 2007, Energy, Environment, and Water Research Center RepThe Cyprus Institute, Nicosia, Cyprus.
27. Levenberg K. A method for the solution of certain nonlinear problems in least squares. Q. Appl. Math. 1944, 2:164-168. QAMAAY, 0033-569X
28. Liu D. Hao Z. Zhu C. Ju Q. Yu Z. On the development of improved artificial neural network model and its application on hydrological forecasting. Proc3rd Int. Conf. on Natural Computation, ICNC 2007 2007, 45-49.
29. 2005, Local water supply, sanitation and sewage: Country report-Cyprus Euro-Mediterranean information system on know-how in the water sector, MEDA Water, Nicosia, Cyprus.
30. Maidment D. Miaou S. Daily water use in nine cities. Water Resour. Res. 1986, 22(6):845-851. WRERAQ, 0043-1397, 10.1029/WR022i006p00845
31. Maidment D. Miaou S. Crawford M. Transfer function models of daily urban water use. Water Resour. Res. 1985, 21(4):425-432. WRERAQ, 0043-1397, 10.1029/WR021i004p00425
32. Maidment D. Parzen E. Monthly water use and its relationship to climatic variables in Texas. Water Resour. Bull. 1984, 19(8):409-418. WARBAQ, 0043-1370
33. Marquardt D. An algorithm for least-squares estimation of nonlinear parameters. SIAM J. Appl. Math. 1963, 11:431-444. SMJMAP, 0036-1399, 10.1137/0111030
34. 2005, Matlab help files. Mathworks, Cambridge, MA.
35. Miaou S. A class of time series urban water demand models with non-linear climatic effects. Water Resour. Res. 1990, 26(2):169-178. WRERAQ, 0043-1397
36. Oh H. Yamauchi H. An economic analysis of the patterns and trends in water consumption within the service area of the Honolulu Board of Water Supply. 1974, and Univ. of Honolulu Rep. No.84, Univ. of Honolulu, Honolulu, Hawaii.
37. Piotrowski A. Napiórkowski J.J. Rowiński P.M. Flash-flood forecasting by means of neural networks and nearest neighbor approach-A comparative study. Nonlinear Processes Geophys. 2006, 13(4):443-448. 1023-5809, 10.5194/npg-13-443-2006
38. Powell M. Restart procedures for the conjugate gradient method. Math. Program. 1977, 12:241-254. MHPGA4, 0025-5610, 10.1007/BF01593790
39. Pulido-Calvo I. Montesinos P. Roldán J. Ruiz-Navarro F. Linear regressions and neural approaches to water demand forecasting in irrigation districts with telemetry systems. Biosyst. Eng. 2007, 97(2):283-293. BEINBJ, 1537-5110, 10.1016/j.biosystemseng.2007.03.003
40. Pulido-Calvo I. Portela M.M. Application of neural approaches to one-step daily flow forecasting in Portuguese watersheds. J. Hydrol. 2007, 332:1-15. JHYDA7, 0022-1694, 10.1016/j.jhydrol.2006.06.015,
41. Pulido-Calvo I. Roldan J. Lopez-Luque R. Gutierrez-Estrada J. Demand forecasting for irrigation water distribution systems. J. Irrig. Drain. Eng. 2003, 129(6):422-431. JIDEDH, 0733-9437, 10.1061/(ASCE)0733-9437(2003)129:6(422)
42. Riedmuller M. Braun H. A direct adaptive method for faster backpropagation learning: The RPROP algorithm. Proc. of the IEEE Int. Conf. on Neural Networks 1993, 1:586-591. and IEEE, New York, Vol.
43. Savvides L. Dorflinger G. Alexandrou K. The assessment of water demand in Cyprus 2001, and Dept. of Cyprus Water Development Publication/.
44. Sivakumar S.K. The great divider. 2004, The Hindu, May 16, 2004.
45. Smith J. A model of daily municipal water use for short-term forecasting. Water Resour. Res. 1988, 24(2):201-206. WRERAQ, 0043-1397, 10.1029/WR024i002p00201
46. Socratous G. Management of water in Cyprus. 1st Congress Balears Water: Perspectives for the Future 2005, paper presented at the .
47. Tsiourtis N. Desalination: The Cyprus experience. European Water 2004, 8:39-45.,
48. Yue L. Zhang H. Wang L. Application of particle swarm optimization in urban water demand prediction. Journal of Tianjin University Science and Technology 2007, 40(6):742-746.
49. Zhou S. McMahon T. Walton A. Lewis J. Forecasting daily urban water demand: A case study of Melbourne. J. Hydrol. 2000, 236(3-4):153-164. JHYDA7, 0022-1694, 10.1016/S0022-1694(00)00287-0