Design of Groundwater Level Monitoring Network, Using the Model of Least Squares Support Vector Machine (LS-SVM)

Document Type : Research Paper


1 Ms.C student of water resources management, University of Birjand.

2 Assistant Professor of Water Engineering Department., University of Birjand.


The present study presents a methodology for the design of long-term groundwater head monitoring networks to reduce spatial redundancy in which the additional wells if not sampled, the error related to groundwater level estimation would be negligible. This method is based on Support Vector Machine, and founded upon the statistical learning theory. Throughout the study, some 63 quantitative data, observation wells as well as meteorological parameters (precipitation and evaporation) of Ramhormoz plain (in a 7-year period) were employed to evaluate the performance of Least Squares Support Vector Machine model (LS-SVM) in the groundwater observation well network design concept. Different combinations of parameters affecting the ground water level were assessed using the model LS-SVM. The optimal combination of LSSVM model with RBF Kernel function carries such performance parameters as R2=0.9992, MAE=0.3405. Then, using Function Approximation Optimum, a number of 42 observation wells were pinpointed to apply the appropriate spatial monitoring in the plain of RAMHORMOZ.


Main Subjects

Asefa, T., W. Kemblowski, M., Urroz, G., Mckee, M., and Khalil, A., (2004). Support vectors machines(SVM) for monitoring network design. Journal of Groundwater .43(3),413-422.
Asefa, T., W. Kemblowski, M., Urroz, G., Mckee, M., and Khalil, A., (2005). Support vectors-based groundwater head observation networks design. Journal of Water Resources Research.(40).
Bashi-Azghadi, S. N. and Kerachian, R. (2010). Locating monitoring wells in groundwater systems using embedded optimization and simulation models. Science of the Total Environment. 408: 2189–2198.
Cristianini, N. and Shawe-Taylor, J. (2000).An Introduction to Support Vector Machines. Cambridge university press. NEW YORK.
Guo, Y., Wang, j., Yin, X., (2011). Optimizing the ground water monitoring network using MSN Theory. Procedia Social and behavioral Sciences. 21, 240-242.
H.Hwang, S., H. Ham, D., and H. Kim, J. (2012). Forecasting Performance of LS-SVM For Nonlinear Hydrological Time Series. J.CivilEng.,16(5), 870-882.
Hatef, M. R. (2007). Final Report of project study Plain RAMHORMOZ hydroclimatology balance, Ahvaz, Khuzestan Water and Power Organization.
Khashei-Siuki, A., Ghahraman, B., and Kouchakzadeh, M. (2013). Comparison of ANN, ANFIS and Regression models to estimate groundwater  level of Neyshaboor aquifer.Journal of lrrigation and Drainage, 7(1), 10-22. (In Farsi)
Kisi, O. (2012).Least squares support vector machine for modeling daily reference evapotranspiration. Irrig Sci.
Masoumi, F. and Kerachian, R. (2007). Optimal Groundwater Monitoring Network Design Using the Entropy Theoty. Journal of Water & Wastewater,65. (In Farsi).
Mellit, A., Massi Pavan, A., and Benghanem, M. (2013). Least squares support vector machine for short-term prediction of meteorological time series. Theor Appl Climatol,111, 297–307.
Seifi, A. (2010). Developing an Expert System for Predicting Daily Reference Evapotranspiration Using Support Vector Machines (SVM) in Comparison with ANFIS, ANN and Empirical Methods. M. S. in Irrigation and drainage Engineering, Tarbiat Modares University, Tehran. (In Farsi)
Shiloh Shah, R. (2007).Support vector machines for classification and regression,Master of science,computer science,Mcgill university Montreal, Quebec.
Suykens, J. A. K., Gestel, T. V., Brabanter, J. D., Moor, B. D., and Vandewalle, J. (2002). Least Squares Support Vector Machines. Copyright by World Scientific Publishing Co. Pie. Ltd. (pp.58,72-75, 98-99).
Zhou, Y., Dong, D., Lio, and J. Li, W. (2013). Upgrading a regional groundwater level monitoring network for Beijing Plain, China. GEoSCIENCE FRONTIERS, 4,127-138.