Application of Least Square Support Vector Machine (LSSVM) for Determination of Evaporation Losses in Reservoirs

Author(s)
Pijush Samui

Abstract

This article adopts Least Square Support Vector Machine (LSSVM) for prediction of Evaporation Losses (EL) in reservoirs. LSSVM is firmly based on the theory of statistical learning, uses regression technique. The input of LSSVM model is Mean air temperature (T) (?C), Average wind speed (WS)(m/sec), Sunshine hours (SH)(hrs/day), and Mean relative humidity(RH)(%). LSSVM has been used to compute error barn of predicted data. An equation has been developed for the determination of EL. Sensitivity analysis has been also performed to investigate the importance of each of the input parameters. A comparative study has been presented between LSSVM and artificial neural network (ANN) models. This study shows that LSSVM is a powerful tool for determination EL in reservoirs.

This article adopts Least Square Support Vector Machine (LSSVM) for prediction of Evaporation Losses (EL) in reservoirs. LSSVM is firmly based on the theory of statistical learning, uses regression technique. The input of LSSVM model is Mean air temperature (T) (?C), Average wind speed (WS)(m/sec), Sunshine hours (SH)(hrs/day), and Mean relative humidity(RH)(%). LSSVM has been used to compute error barn of predicted data. An equation has been developed for the determination of EL. Sensitivity analysis has been also performed to investigate the importance of each of the input parameters. A comparative study has been presented between LSSVM and artificial neural network (ANN) models. This study shows that LSSVM is a powerful tool for determination EL in reservoirs.

Keywords

Evaporation Losses, Least Square Support Vector Machine, Prediction, Artificial Neural Network

Evaporation Losses, Least Square Support Vector Machine, Prediction, Artificial Neural Network

Cite this paper

nullP. Samui, "Application of Least Square Support Vector Machine (LSSVM) for Determination of Evaporation Losses in Reservoirs,"*Engineering*, Vol. 3 No. 4, 2011, pp. 431-434. doi: 10.4236/eng.2011.34049.

nullP. Samui, "Application of Least Square Support Vector Machine (LSSVM) for Determination of Evaporation Losses in Reservoirs,"

References

[1] E. D. Eaton, “Control of Evaporation Losses,” United States Government Printing Office, Washington, USA, 1958.

[2] V. P. Singh and C.Y. Xu, “Evaluation and Generalization of 13 Mass Transfer Equations for Deter-mining Free Water Evaporation,” Hydrological Processes, Vol. 11, 1997, pp. 311-323.
doi:10.1002/(SICI)1099-1085(19970315)11:3<311::AID-HYP446>3.0.CO;2-Y

[3] R. B. Stewart and W. R. Rouse, “A Simple Method for Determining the Evapora-tion from Shallow Lakes and Ponds,” Water Resources Research, Vol. 12, 1976, pp. 623- 627. doi:10.1029/WR012i004p00623

[4] H. A. R. D. Bruin, “A Simple Model for Shallow Lake Evaporation,” Journal of Applied Meteorology, Vol. 17, 1978, pp. 1132- 1134.
doi:10.1175/1520-0450(1978)017<1132:ASMFSL>2.0.CO;2

[5] M. E. Anderson and H. E. Jobson, “Comparison of Techniques for Estimating Annual Lake Evaporation Using Climatological Data,” Water Resources Research, Vol.18, 1982, pp. 630-636. doi:10.1029/WR018i003p00630

[6] W. Abtew, “Eva-poration Estimation for Lake Okee- chobee in South Florida,” Journal of Irrigation and Drainage Engineering, Vol. 127, 2001, pp. 140-147.
doi:10.1061/(ASCE)0733-9437(2001)127:3(140)

[7] S. Murthy and S. Gawande, “Effect of Metrological Para-meters on Evaporation in Small Reservoirs ‘Anand Sagar’ Shegaon - A Case Study,” Journal of Prudushan Nirmulan, Vol. 3, No. 2, 2006, pp. 52-56.

[8] S. Deswal and P. Mahesh, “Artificial Neural Network Based Mod-eling of Evaporation Losses in Reservoirs,” International Journal of Mathematical, Physical and Engineering Sciences, Vol. 2, No.4, 2008, pp.177-181.

[9] D. Park and L. R. Rilett, “Forecasting Freeway Link Travel Times with a Multi-Layer Feed forward Neural Network,” Computer Aided Civil and Infrastructure Engineering, Vol. 14, 1999, pp.358 - 367.
doi:10.1111/0885-9507.00154

[10] V. Kecman, “Learn-ing and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models,” The MIT press, Cambridge, England, 2001.

[11] J. A. K. Suykens, L. Lukas, D. P. Van, M. B. De and J. Vandewalle, “Least Squares Support Vector Machine Classifiers: A Large Scale Algorithm,” Proceedings of European Conference on Circuit Theory and Design, Stresa, Italy, 1999, pp. 839-842.

[12] A. J. Smola, “Learning with Kernels,” Ph.D. dissertation, GMD, Birlinghoven, Germany, 1998.

[13] X. D. Wang and M. Y. Ye, “Nonlinear Dy-namic System Identification Using Least Squares Support Vector Machine Regression,” Proceedings of the Third International Conference on Machine Learning and Cy-bernetics, Shanghai, 2004, pp. 26-29.

[14] P. Samui and T. G. Sitharam, “Least-Square Support Vector Machine Applied to Settlement of Shallow Foundations on Cohe-sionless Soils,” International Journal of Numerical and Analytical Method in Geomechanics, Vol. 32, No.17, 2008, pp. 2033-2043. doi:10.1002/nag.731

[15] A. Baylara, D. Hanbay and M. Batan, “Application of Least Square Support Vector Machines in the Prediction of Aeration Performance of Plunging Overfall Jets from Weirs”, Expert Systems with Applications, Vol. 36, No.4, 2009, pp. 8368-8374. doi:10.1016/j.eswa.2008.10.061

[16] V. Vapnik and A. Lerner, “Pattern Recognition Using Generalizd Portait Method,” Automation and Remote Control, Vol. 24, 1963, pp. 774-780.

[17] J. A. K. Suykens, B. J. De, L. Lukas and J. Vandewalle, “Weighted Least Squares Support Vector Machines: Robustness and Sparse Approximation”, Neurocomputing, Vol. 48, No. 1-4, 2002, pp. 85-105.
doi:10.1016/S0925-2312(01)00644-0

[18] A. Smola and B. Scholkopf, “On a Kernel Based Method for Pattern Recognition, Regression, Approximation and Operator Inversion,” Algorithmica, Vol. 22, 1998, pp. 211-231. doi:10.1007/PL00013831

[19] V. N. Vapnik , “Statistical Learning Theory,” Wiley, New York, 1998.

[20] S. Y. Liong, W. H. Lim and G. N. Paudyal, “River Stage Fore-casting in Bangladesh: Neural Network Approach,” Journal of Computing in Civil Engineering, Vol. 14, No.1, 2000, pp.1-8.
doi:10.1061/(ASCE)0887-3801(2000)14:1(1)