Simulating the groundwater table of Sarakhs plain with combination of geostatistical and artificial intelligence methods

Document Type : Complete scientific research article


1 Department of Nature Engineering , Faculty of Agriculture, University of Torbat Heydarieh,

2 Department of Nature Engineering , Faculty of Agriculture, University of Torbat Heydarieh, Torbat Heydarieh, Iran

3 University of Tehran, Faculty of Natural Resources

4 University of Torbat Heydarieh


Background and objectives: Simulation of groundwater is very important in order to groundwater table prediction, hydrogeological and management studies, construction of structures, agricultural use, and access to high quality groundwater. In recent decades, artificial intelligence models have been tested for simulation of aquifers due to the complex and nonlinear properties of groundwater systems. The purpose of this study is comparison the different models of artificial intelligence (artificial neural network, multi-layer perceptron, radial basis function and neuro-fuzzy) and its composition with geostatistics methods to modeling the groundwater table in the Sarakhs plain. Investigation of recent studies shows that simulation of groundwater level with artificial intelligence methods in different regions has different results.
Materials and Methods: Sarakhs County with more than 5000 Km2 area is located in 60°15' to 60°30' eastern longitude ‎and 35°55' to 36°40' northern latitude. ‎ Sarakhs Plainﹸs aquifer is unconfined type and shaped from a layer of alluvial. In this research, groundwater level data of 18 wells, rainfall and potential evaporation in statistical period (1992- 2016) were used. The affected area of each climatology station determined by Thiessenﹸs method and climate data of each station generalized to wells which situated in related polygon. The artificial intelligence models that used in this study were Multi-Layer Perceptron (MLP), Radial Basis Function (RBF) and Neuro Fuzzy (NF) and geostatistics methods were Kocriging, Kriging and Inverse Distance Weighting. 70 percent of the input data for training of models and the remaining 30 percent were used for ‎testing of them. To assessment of the results of simulations with Artificial Intelligence models the criteria of ‎correlation coefficient (R), Mean Absolute Error (MAE) and Coefficient of Determination (R2) ‎and for evaluation of geostatistics method the criteria of ‎‏ ‏Root Mean Square Error (RMSE) and‎‏ ‏‎ Mean Square ‎Error (MSE) were used. ‎
Results: The results showed that the multi-layer perceptron model is more accurate than other models, according to R=0.77, R2 = 0.62 and MAE = 0.80. To determination of the best geostatistical model, for spatial prediction of the groundwater level, the results of multi-layer perceptron model used as input data. The results showed that Kriging method with RMSS= 1 and RMS= 0.066, is better model to spatial simulation of groundwater level in Sarakhs plain and base of Kriging method, the maps of groundwater level in each year was designed. Assessment of these maps showed the most decline of groundwater level is in the north parts of ‎Skaraks plain and south part of this Palin has a little declining of groundwater level. ‎
Conclusion: The combination of the MLP model and the Kriging interpolation method is a suitable and low cost solution for simulating of the groundwater level in the Sarakhs Plain. It is suggested that if possible more dependent variables be used to increase the accuracy of artificial intelligence models. Also, for better prediction of groundwater level, the other artificial intelligence models with different algorithms ‎should be used. ‎


  1. 1.Ahmadi, S.H., and Sedghamiz, A. 2008. Application and evaluation of Kriging and cokriging methods on groundwater depth mapping. Environ. Monit. Assess. 138: 1-3. 357-368.

    2.Asghari Moghaddam, A., Fijani, E., and Nadiri, A. 2015. Optimization of DRASTIC model by artificial intelligence for groundwater vulnerability assessment in Maragheh-Bonab Plain. Geosciences. 24: 94. 169-176. (In Persian)

    3.Azareh, A., Zehtabian, Gh.R., Nazari Samani, A.A., and Khosravi, H. 2015. Desertification monitoring in Garmsar plain with emphasis on water and agriculture criteria. J. Range Water. Manage. 68: 3. 427-439. (In Persian)

    4.Bahremand, A. 2016. HESS Opinions: Advocating process modeling andDe-emphasizing parameter estimation. Hydrol. Earth Syst. Sci. 20: 1433-1445.

    5.Bameri, A., Piri, H., and Ganji, F. 2015. Assessment of groundwater pollution in Bajestan Plains for agricultural purposes using indicator Kriging. J. Water Soil Cons. 22: 1. 211-229. (In Persian)

    6.Chang, X., Hui, J., Rong, W., and Hao, W. 2013. Groundwater level prediction based on BP and RBF neural network. J. Appl. Sci. Engin. Res. 3: 2. 263.269.

    7.Dehghani, R., and Noorali, A. 2016. Comparison of geo-Statistical methods and artificial neural network in estimating groundwater level (Case study: Nourabad Plain, Lorestan). J. Environ. Sci. Technol. 18: 1. 31-43. (In Persian)

    8.Delbari, M., Boustanian, M., and Afrasiayab, P. 2016. Investigation of spatial and temporal variations and zonation of ground water level in Kohpaye-Segzi Aquifer (Isfahan Province). Geographic Space. 52: 15. 305-324.(In Persian)

    9.Fakhari, M., Saadat, S., and Fazael Valipour, M.E. 2014. The effect of Dosty dam construction on the groundwater resources of Sarakhs Plain. International conference on sustainable development, strategies and challenges with focus on agriculture, natural Resources, environment and tourism, Tabriz. 9p. (In Persian)

    10.Habibi, M.H., Nadiri, A.A., Asghari Moghaddam, A., and Naderi, K. 2016. Combination of geostatistical and artificial intelligence methods for predicting spatiotemporal water level in the Hadishahr plain. Iran-Watershed Management Science & Engineering. 10: 32. 27-32. (In Persian)

    11.Komasi, M., Goudarzi, H., and Behniya, A. 2017. Investigation spatial- temporal fluctuation ground water level by support vector machine and kriging method (Case study: Silakhor plain).J. Water Soil Cons. 24: 4. 195-209.(In Persian)

    12.Kord, M., and Asghari Moghaddam, A. 2015. Evaluation of drinking water quality of Ardabil plain aquifer by cokriging and Fuzzy Logic. J. Water Soil Cons. 21: 5. 225-240. (In Persian)

    13.Lohani, A.K., and Krishan, G. 2015. Application of artificial neural network for ground water level simulation in Amritsar and Gurdaspur Districts of Punjab, India. J. Earth Sci. Clim. Change. 6: 4. 1-5.

    14.15.Moslemzadeh, M., Salarijazi, M., and Soleymani, S. 2011. Application and assessment of kriging and cokriging methods on groundwater level estimation. J. Amer. Sci. 7: 7. 34-39.   

    16.Mozafari, Gh., and Behzadi Karimi, H. 2017. Estimation of groundwater levels in Bayza plain using geostatistical methods. J. Geoghraph. Environ. Stud. 6: 21. 145-163. (In Persian)

    17.Nadiri, A., Sedghi, Z., and Kazemian, N. 2017. Optimization of DRASTIC method using ANN to evaluating of vulnerability of multiple Varzqan Aquifer. J. Eco Hydrol. 4: 4. 1089-1103. (In Persian)

    1. 19.Noor, H., Chezgy, J., Bagheriyan Kalat, A., Rajaie, S.H., and Seddigh, R. 2018, Assessment of quantitative status of groundwater resources in the Ghareghoom basin, Third National Conference of Soil and Water conservation, Tehran, Iran.

    20.Notters, M., Brus, D.J., and Voshaar, O. 1995. A comparison of kriging, cokriging and combined with regression for spatial interpolation of horizon depth with censored observations, Geoderma. 67: 3. 227-246.

    21.Pourseyadi, A., and Kashkuli, H.A. 2012, Studying of groundwater conditions in Jiroft Basin with MODFLOW, J. Irrig. Sci. Engin.32: 2. 51-63. (In Persian)

    22.Ramezani Charmahineh, A., and Zounemat-Kermani, M. 2017. Evaluation of the efficiency of support vector regression, multi-layer perceptron neural network and multivariate linear regression on groundwater level prediction (Case study: Shahrekord Plain). J. Water. Manage. Res. 8: 15. 1-12. (In Persian)

    23.Sun, Y., Wendi, D., Kim, D.E., and Liong, S.Y. 2015. Application of artificial neural networks in groundwater table forecasting–a case study in Singapore swamp forest. Hydrology and Earth System Science. 5: 12. 9317-9336.

    24.Suryanarayana, Ch., Sudheer, Ch., Mahammood, V., and Panigrahi, B.K. 2014. An integrated wavelet support vector machine for groundwater level prediction in Visakhapatnam, India. Neurocomputing. 15: 145. 324-335.

    25.Yu, H., Wen, X., Feng, Q., Ravinesh, D., Jianhua, S., and Min, W. 2018. Comparative study of Hybrid-Wavelet artificial intelligence models for monthly groundwater depth forecasting in extreme arid regions, Northwest China. Water Recourses Management. 23: 1. 301-323.

    26.Zamani Ahmad Mahmoodi, R., Akhondali, A.M., Samadi Borojeni, H. and Zareei, H. 2013. Estimation of the groundwater level by using combined geostatistics with Artificial Neural Networks (Case study: Shahrekord Plain). J. Irrig. Sci. Engin. 36: 1. 45-56. (In Persian)

    27.Zare Abyaneh, H., and Bayat Varkeshi, M. 2013. Development and application of statistical and neural, Fuzzy, Genetic Algorithm models in estimation of spatial distribution of water table level. J. Water Soil Cons. 20: 4. 1-25.(In Persian)