Design of a Neural Network Model for the Determination of Unconfined Aquifer Parameters

Subject Areas : Subjects

Tahere Azari ¹ (دانشجوی دکترای زمین شناسی گرایش آبشناسی، بخش علوم زمین، دانشکده علوم، دانشگاه شیراز)
Nozar Samani ² (استاد بخش علوم زمین، دانشکده علوم، دانشگاه شیراز)

Received: 2016-06-25 Accepted : 2016-06-25 Published : 2016-06-21

Keywords: Artificial neural network, Aquifer parameters, principal component analysis (PCA), Levenberg–Marquardt (LM) training algorithm, Pumping test,

Abstract :

In this paper, an Artificial Neural Network (ANN) is designed for the determination of unconfined aquifer parameters: transmissibility, storage coefficient, specific yield, and delay index. The network is trained for the well function of unconfined aquifers by the back propagation technique and adopting the Levenberg–Marquardt (LM) optimization algorithm. By applying the principal component analysis (PCA) on the training data sets the topology of the network is reduced and fixed to [3×6×3] regardless of number of records in the pumping test data. The network generates the optimal match point coordinates for any individual real pumping test data set. The match point coordinates are then incorporated with Boulton analytical solution (1963) and the aquifer parameter values are determined. The generalization ability and performance of the developed network is evaluated with 100/000 sets of synthetic data and its accuracy is compared with that of the type curve matching technique by two sets of real field data. The proposed network is recommended as a simpler and more reliable alternative for the determination of unconfined aquifer parameters compare to the conventional type-curve matching techniques.

References:

1. Boulton, N.S. 1954. The drawdown of the water table under non-steady conditions near a pumped well in an unconfined formation. Proc, Instn. Civ. Eng. 3: 574.


2. Boulton, N.S. 1963. Unsteady radial flow to a pumped well allowing for delayed yield from storage. 472-477.


3. Cattell, R.B. 1966. The scree test for the number of factors. Multivar. Behav. Res. 1: 245-276.


4. Chris, D., and H. Xiaofeng. 2004. K-Means clustering via principal component analysis. In proceedings of the 21st Int. Conf. Machine Learning, Banff, Canada.


5. Coulibaly, P., F. Anctil, R. Aravena, and B. Bobee. 2001. Artificial neural network modeling of water table depth fluctuations. Water Resour. Res. 37: 885–896.


6. Daliakopoulos, I.N., P. Coulibaly, and I.K. Tsanis. 2005. Groundwater level forecasting using artificial neural networks. J Hydrol. 309: 229–240.


7. De Ridder, N.A. 1966. Analysis of the pumping test De Vennebulten near Varsseveld (in Dutch). Inst. Land and Water Manag. Res, Wageningen, Report no. 335, 5 pp.


8. Gambolati, G. 1976. Transient free surface flow to a well: An analysis of theoretical solutions. Water Resour. Res. 12: 27-39.


9. Hantush, M.S., and C.E. Jacob. 1955. Non-steady radial flow in an infinite leaky aquifer. Trans Am Geophys Union. 36: 95–100.


10. Haykin, S. 1999. Neural networks: a comprehensive foundation. Prentice-Hall: Englewood Cliffs, N.J.


11. Hornik, K., M. Stinchcombe, and H. White. 1989. Multilayer feed forward networks are universal approximators. Neural Networks. 2: 359–366.


12. Lin, G.F., and G.R. Chen. 2005. Determination of aquifer parameters using radial basis function network approach. J Chinese Inst. Eng. 28: 241-249.


13. Lin, G.F., and G.R. Chen. 2006. An improved neural network approach to the determination of aquifer parameters. J. Hydrol. 316: 281–289.


14. Lin, H.T., K.Y. Ke, Ch.H. Chen, Sh.Ch. Wu, and Y.Ch. Tan. 2010. Estimating anisotropic aquifer parameters by artificial neural networks. Hydrol. Process. 24: 3237–3250.


15. McCulloch, W., and W. Pitts. 1943. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys. 5: 113–115.


16. Maier, H.R., and G.C. Dandy. 1999. Empirical comparison of various methods for training feed-forward neural networks for salinity forecasting. Water Resour Res. 32: 2591–2596.


17. Maier, H.R., and G.C. Dandy. 2000. Neural networks for the prediction and forecasting of water resources variables: A review of modeling issues and applications. Environ Modell Softw. 15: 101–124.


18. Neuman, S.P. 1972. Theory of flow in unconfined aquifers considering delayed response of the water table. Water Resour Res. 8: 1031-1045.


19. Neuman, S.P. 1973. Supplementary comments on theory of flow in unconfined aquifers considering delayed response of the water table. Water Resour. Res. 9: 1102-1103.


20. Neuman, S.P. 1975. Analysis of pumping test data from anisotropic unconfined aquifers considering delayed gravity response. Water Resour Res. 11: 329-342.


21. Neuman, S.P. 1979. Perspective on delayed yield. Water Resour Res 15: 899-908.


22. Prickett, T.A. 1965. Type curve solution to aquifer tests under water table conditions. Ground Water. 3.


23. Samani, N., M. Gohari-Moghadam, and A.A. Safavi. 2007. A simple neural network model for the determination of aquifer parameters. J Hydrol. 340: 1–11.


24. Streltsova, T.D. 1972a. Unconfined aquifer and slow drainage. J Hydrol. 16: 117-124.


25. 7. Streltsova, T.D. 1972b. Unsteady radial flow in an unconfined aquifer. Water Resour. Res. 8: 1059-1066.


26. Streltsova, T.D. 1973. On the leakage assumption applied to equations of groundwater flow. J. Hydrol. 20: 237-253.


27. Streltsova, T. D. 1976. Progress in research on well hydraulics. Advances in groundwater hydrology, Am. Water Resour. Assoc. 15-28.


28. Theis, C.V. 1935. The relationship between the lowering of the piezometric surface and the rate and duration of discharge of a well using ground-water storage. Trans. Am. Geophys Union. 16: 519–524.


29. Todd, D. K., and L. W. Mays. 2005. Groundwater hydrology. John Wiley & Sons, Inc., N.Y, USA.


30. Toth, E., A. Brath, and A. Montanari. 2000. Comparison of short-term rainfall prediction models for real-time flood forecasting. J. Hydrol. 239: 132–147.