Kharazmi Journal of Earth Sciences

Kharazmi Journal of Earth Sciences

Design of a supervised artificial intelligence committee machine to estimate hydrodynamic parameters of confined aquifers

Author
Tahereh Azari
Kharazmi university
10.22034/KJES.2025.11.1.106211
Abstract
Accurate estimation of hydrodynamic parameters is essential for sustainable aquifer development. Since Theis (1935), the Type Curve Matching Technique (TCMT) has been used to estimate aquifer parameters. This method is associated with graphical errors. In this study, a supervised AI committee machine was used to eliminate errors and accurately estimate the hydrodynamic parameters of confined aquifers with high ability to approximate functions as an alternative to the conventional TCMT method and existing AI methods. In this study, pumping test data were considered as input components and the coordinates of the optimal point were considered as the output. To reduce the dimensions of the input components, the principal component analysis (PCA) technique was used. Then, the matching point coordinates were combined with the analytical solution of Theis (1935) and the values of the aquifer parameters were calculated. To develop this machine, in the first step, three ANNs with different training algorithms, Levenberg–Marquardt (LM), gradient descent (GD), resilient back-propagation (RP), were developed to determine the match point and estimate the hydrodynamic parameters of the confined aquifer. Based on the modeling results, all models showed a good approximation of the hydrodynamic parameters of the confined aquifer. Then, in the second step, considering the complexity of hydrogeological systems, a committee machine consisting of three artificial intelligence models was designed and built, which used the capabilities of all three models to determine the hydrodynamic parameters of the confined aquifers. The models' outputs were combined using a supervised nonlinear combiner, yielding highly accurate final results. The results showed that the proposed committee machine model is more accurate, and better alternative to TCMT methods and artificial intelligence methods in determining the optimal match point and estimating the hydrodynamic parameters of the confined aquifer.
Keywords
Artificial neural network
supervised artificial intelligence committee machine
pumping test
type curve matching method
confined aquifer parameters
Subjects
ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. 2000a. Artificial neural networks in hydrology, I: Preliminary concepts. Journal of Hydrology. Engineering 5(2), 115–123.
ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. 2000b. Artificial neural networks in hydrology, II: Hydrologic applications. Journal of Hydrology Engineering 5(2), 124–137.
Azari, T., Samani, N., 2018. Modeling the Neuman’s well function by an artificial neural network for the determination of unconfined aquifer parameters. Computational Geosciences 22, 1135–1148.
Azari, T., Samani, N., Mansoori, E., 2015. An artificial neural network model for the determination of leaky confined aquifer parameters: an accurate alternative to type curve matching methods. Iran Journal of Science and Technology 39(4), 463-472.
Baird, L., Moore, A., 1999. Gradient descent for general reinforcement learning. Adv Neural Inf Process Syst 11, 968–974.
Bishop, C.M., 1995. Neural Networks for Pattern Recognition. Clarendon Press, Oxford, p. 670.
Boadu, F.K., 1997. Rock properties and seismic attenuation: neural network analysis. Pure Appl Geophys 149, 507–524.
Boadu, F.K., 1998. Inversion of fracture density from field seismic velocities using artificial neural networks. Geophysica 63, 534–545.
Burney, S.M.A., Jilani, T.A., Ardil, C., 2008. Levenberg–Marquardt algorithm for Karachi stock exchange share rates forecasting. International Journal of Computer and Information Engineering 2(4), 1330–1335.
Chen, C.H., Lin, Z.S., 2006. A committee machine with empirical formulas for permeability prediction. Computer and Geoscience 32(4), 485–496.
Coulibaly, P., Anctil, F., Aravena, R., Bobee, B., 2001. Artificial neural network modeling of water table depth fluctuations. Water Resources Research 37(4), 885–896.
Daliakopoulos, I.N., Coulibaly, P., Tsanis, I.K., 2005. Groundwater level forecasting using artificial neural networks. Journal of Hydrology 309(1–4), 229–240.
Dashti, Z., Nakhaei, M., Vadiati, M., Karami, G.H., Kisi, O., 2023. Estimation of unconfined aquifer transmissivity using a comparative study of machine learning models. Water Resources Management 37, 4909-4931.
Davis, J.C., 2002. Statistics and Data Analysis in Geology, 3rd edn. Wiley, New York.
Delnaz, A., Rakhshandehroo, G.R., Nikoo, M.R., 2020. Confined aquifer's hydraulic parameters estimation by a generalized regression neural network. Iranian Journal of Science and Technology - Transactions of Civil Engineering 44(1), 259-269.
Fausett, L., 1994. Fundamentals of neural networks. Prentice-Hall, Englewood Cliffs, NJ.
Haykin, S., 1999. Neural networks: a comprehensive foundation, Prentice-Hall: Englewood Cliffs, NJ.
Hantush, MS., Jacob, CE., 1955. Non-steady radial flow in an infinite leaky aquifer. Trans AmericanGeophys Union 36(1), 95–100.
Kononen, V., 2005. Gradient descent for symmetric and asymmetric multiagent reinforcement learning. Web IntelligenceandAgent Systems 3, 17–30.
Lim, J.S., 2005. Reservoir properties determination using fuzzy logic and neural networks from well data in offshore Korea. Journal of PetroleumScience and Engineering 49(3-4), 182–192.
Lin, G.F., Chen, G.R., 2005. Determination of aquifer parameters using radial basis function network approach. Journal of the ChineseInstitute of Engineers 28(2), 241–249.
Lin, G.F., Chen, G.R., 2006. An improved neural network approach to the determination of aquifer parameters. Journal of Hydrology 316(1–4), 281–289.
Lin, H.T., Ke, K.Y., Chen, C.H., Wu, S.C., Tan, Y.C., 2010. Estimating anisotropic aquifer parameters by artificial neural networks. Hydrological Processes 24(22), 3237–3250.
Mahmoudabadi, H., Izadi, M., Menhaj, M.B., 2009. A hybrid method for grade estimation using genetic algorithm and neural networks. Computational Geosciences1 3(1), 91–101.
Maier, H.R., Dandy, G.C., 1999. Empirical comparison of various methods for training feed-forward neural networks for salinity forecasting. Water Resources Research 32(8), 2591–2596.
Maier, H.R., Dandy, G.C., 2000. Neural networks for the prediction and forecasting of water resources variables: a review of modeling issues and applications. Environmental Modellingand Software 15(1), 101–124.
Maier, H.R., Jain, A., Dandy, G.C., Sudheer, K.P., 2010. Methods used for the development of neural networks for the prediction of water resource variables in river systems: current status and future directions. Environmental Modelling and Software 25(8), 891–909.
Nadiri, A.A., Fijani, E., Tsai, F.T.C., Asghari-Moghaddam, A., 2013. Supervised committee machine with artificial intelligence for prediction of fluoride concentration. Journal of Hydroinformatics 15(4), 1474-1490.
Nadiri, A.A., Naderi, K., Khatibi, R., Gharekhani, M., 2019. Modelling groundwater level variations by learning from multiple models using fuzzy logic. Hydrological Science Journal 64(2), 210-226.
Razavi, S., Tolson, B.A., 2011. A new formulation for feed forward neural networks. IEEE Transactions on Neural Networks 22(10), 1588–1598.
Riedmiller, M., Braun, H., 1993. A direct adaptive method for faster back-propagation learning: the RPROP algorithm. Proc IEEE Conf on Neural Networks.
Rumelhart, D.E., Hinton, G.R., Williams, R.J., 1986. Learning internal representations by error propagation. In: Rumelhart DE, David E, (Eds.), Parallel Distributed Processing MIT Press Massachusetts 318–362.
Samani, N., Gohari-Moghadam, M., Safavi, A.A., 2007. A simple neural network model for the determination of aquifer parameters. Journal of Hydrology 340(1–2),1–11.
Tabari, M.M.R., Azadani, M.N., Kamgar, R., 2020. Development of operation multi-objective model of dam reservoir under conditions of temperature variation and loading using NSGA-II and DANN models: a case study of Karaj/Amir Kabir dam. Soft Computing 24, 12469-12499.
Tabari, M.M.R., Azari, T., Dehghan, V., 2021. A supervised committee neural network for the determination of aquifer parameters: a case study of Katasbes aquifer in Shiraz plain, Iran. Soft Computing 25, 4785–4798.
Tahmasebi, P., Hezarkhani, A., 2012. A hybrid neural networks-fuzzy logic-genetic algorithm for grade estimation. Computers and Geosciences 42, 18–2.
Tayfur, G., Nadiri, A.A., Asghari-Moghaddam, A., 2014. Supervised Intelligent Committee Machine method for hydraulic conductivity estimation. Water Resources Management 28(4), 1173–1184.
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 Amer Geophys Union 16, 519–524.
Toth, E., Brath, A., Montanari, A., 2000. Comparison of short-term rainfall prediction models for real-time flood forecasting. Journal of Hydrology 239(1-4), 132–147.
Wu, W., Dandy, G.C., Maier, H.R., 2014. Protocol for developing ANN models and its application to the assessment of the quality of the ANN model development process in drinking water quality modeling. Environmental Modelling and Software 54, 108–127.
Kharazmi Journal of Earth Sciences
Volume 11, Issue 1 - Serial Number 21
September 2025
Pages 28-46