ABSTRACT

Abstract:This paper evaluates the feasibility of using an artificial neural network (ANN) methodology for estimating the groundwater levels in some piezometers placed in an aquifer in north-western Iran. This aquifer is multilayer and has a high groundwater level in urban areas. Spatiotemporal groundwater level simulation in a multilayer aquifer is regarded as difficult in hydrogeology due to the complexity of the different aquifer materials. In the present research the performance of different neural networks for groundwater level forecasting is examined in order to identify an optimal ANN architecture that can simulate the piezometers water levels. Six different types of network architectures and training algorithms are investigated and compared in terms of model prediction efficiency and accuracy. The results of different experiments show that accurate predictions can be achieved with a standard feedforward neural network trained usung the Levenberg-Marquardt algorithm. The structure and spatial regressions of the ANN parameters (weights and biases) are then used for spatiotemporal model presentation. The efficiency of the spatio-temporal ANN (STANN) model is compared with two hybrid neural-geostatistics (NG) and multivariate time series-geostatistics (TSG) models. It is found in this study that the ANNs provide the most accurate predictions in comparison with the other models. Based on the nonlinear intrinsic ANN approach, the developed STANN model gives acceptable results for the Tabriz multilayer aquifer.

The Harzandat plain is part of the East Azerbaijan province, which lies between Marand and Jolfa cities, northwestern of Iran, and its groundwater resources are developed for water supply and irrigation purposes. The main lithologic units consist chiefly of limestone, dolomite, shale, conglomerate, marl, and igneous rocks. In order to evaluate the quality of groundwater in study area, 36 samples were collected and analyzed for various ions. Chemical indexes like sodium adsorption ratio, percentage of sodium, residual sodium carbonate, and permeability index were calculated. Based on the analytical results, groundwater in the area is generally very hard, brackish, high to very high saline and alkaline in nature. The abundance of the major ions is as follows: Cl(-) >HCO3(-)>SO4(2-) and Na(+) >Ca(2+) >Mg(2+) >K(+). The dominant hydrochemical facieses of groundwater is Na(-)Cl type, and alkalis (Na(+), K(+)) and strong acids (Cl(-), SO4(2-) are slightly dominating over alkali earths (Ca(2+), Mg(2+)) and weak acids (HCO3(-), CO3(2-). The chemical quality of groundwater is related to the dissolution of minerals, ion exchange, and the residence time of the groundwater in contact with rock materials. The results of calculation saturation index by computer program PHREEQC shows that nearly all of the water samples were supersaturated with respect to carbonate minerals (calcite, dolomite and aragonite) and undersaturated with respect to sulfate minerals (gypsum and anhydrite). Assessment of water samples from various methods indicated that groundwater in study area is chemically unsuitable for drinking and agricultural uses.

No abstract