A simple neural network model for the determination of aquifer parameters

Abstract

A simple artificial neural network (ANN) model is developed for the determination of non-leaky confined aquifer parameters by normalizing and applying the principal component analysis (PCA) on adopted training data pattern from Lin and Chen [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]. The proposed network uses faster Levenberg–Marquardt training algorithm instead of gradient descent. The application of PCA highly reduced the network topology so that it has only one neuron in the input layer and eight neurons in the hidden layer regardless of the number of drawdown records in the pumping test data. The network trained with 10,205 training sets and tested with 2000 sets of synthetic data. The network generates the coordinates of the match point for any individual pumping test case study and then the aquifer parameters are calculated using Theis’ equation. The simple ANN trains faster and determines the coordinate of the match point more accurately because of the simplified topology and LM training algorithm. The accuracy, generalization ability and reliability of the proposed network is verified by two sets of real-time field data and the results are compared with that of Lin and Chen as well as graphical methods of aquifer parameters estimation. The proposed ANN appears to be a simpler and more accurate alternative to the type curve-matching techniques and previous ANN methods.