View article

Accurate determination of hydraulic parameter values is the first step to the sustainable 13 development of an aquifer. Since Theis (1935), type curve matching technique (TCMT) has been 14 used to estimate the aquifer parameters from pumping test data. The TCMT is subjected to 15 graphical error. To eliminate the error an Artificial Neural Network (ANN) is developed as an 16 alternative to the conventional TCMT by modeling the Bourdet-Gringaten’s well function for the 17 determination of the fractured double porosity aquifer parameters. The neural network model is 18 developed in a six-step protocol based on multi-layer perceptron (MLP) networks architecture and 19 is trained for the well function of double porosity aquifers by the back propagation method and the 20 Levenberg-Marquardt optimization algorithm. By applying the principal component analysis on 21 the training input data and through a trial-and-error procedure the optimum structure of the 22 network is fixed with the topology of [3× 6× 3]. The replicative, predictive and structural validity 23 of the developed network are evaluated with synthetic and real field data. The developed network 24