Estimating anisotropic aquifer parameters by artificial neural networks

Abstract

Abstract:In recent years, many approaches have been developed using the artificial neural networks (ANN) model incorporated with the Theis analytical solution to estimate the effective hydrological parameters for homogeneous and isotropic porous media, such as the Lin and Chen approach (ANN approach) and the principal component analysis (PCA)-ANN approach. The above methods assume a full superimposition of the type curve and the observed drawdown and try to use the first time-drawdown data as a match point to make a fine approximation of the effective parameters. However, using first time-drawdown data or early time-drawdown data does not always allow for an accurate estimation of the hydrological parameters, especially for heterogeneous and anisotropic aquifers. Therefore, this article corrects the concept of the superimposed plot by modifying the ANN approach and the PCA-ANN approach, as well as incorporating the Papadopoulos analytical solution, to estimate the transmissivities and storage coefficient for anisotropic, homogeneous aquifers. The ANN model is trained with 4000 training sets of the well function, and tested with 1000 sets and 300 sets of synthetic time-drawdown generated from the homogeneous and heterogeneous parameters, respectively. In situ observation data from the time-drawdown at station Shi-Chou on the Choushui River alluvial fan, Taiwan, is further adopted to test the applicability and reliability of the proposed methods, as well as provide a basis for comparison with the Straight-line method and the Type-curve method. Results suggest that both of the modified methods perform better than the original ones, and using late time-drawdown to optimize the effective parameters is shown to be better than using early time-drawdown. Additionally, results indicate that the modified ANN approach is better than the modified PCA-ANN approach in terms of precision, while the efficiency of the modified PCA-ANN approach is approximately three times better than that of the modified ANN approach.

Multivariate approaches optimize locations of groundwater pumping facilities for different hydrogeological scales

“…However, Lin et al . () pointed out that a drawback of the ANN and PCA‐ANN approach (Lin and Chen ; Samani et al ., ) so the precision of the estimated parameters is insufficient. Therefore, Lin et al .…”

“…Therefore, Lin et al . () further modified the ANN (Lin and Chen, ) and PCA‐ANN (Samani et al ., ) approach to increase the precision of the estimation parameters for the anisotropic, homogenous aquifer. Hence, this study employed the modified ANN approach to estimate the effective aquifer parameters using drawdown data from six observation wells for the pumping tests.…”

“…For the training process of the back‐propagation algorithm, Lin et al . () determined that the trained range of the modified ANN output log(1/ u xy ) was selected from −0.3 to 4.0 and that the ANN training process was repeated for each log(1/ u xy ) with the drawdown record point. Once a specific of the best record data of the trained ANN was determined, the W ( u j ) value was calculated by Equation .…”

“…Lin et al . () modified the concept of superimposed plots and extended the application of previous research (Lin and Chen, ; Samani et al ., ) so that the modified ANN and the modified PCA‐ANN were applied to estimate the parameters for homogeneous, anisotropic aquifers. In addition, Lin et al .…”

“…In addition, Lin et al . () pointed out that the precision optimized by the modified ANN approach is better than that with the modified PCA‐ANN approach.…”