×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerSafwan-Zubair area is regarded as one of the important agricultural areas in Basrah province, South of Iraq. The aim of this study is to predict groundwater level in this area using ANNs model. The data required for building the ANNs model are generated using MODFLOW model (V.5.3). MODFLOW model was calibrated based on field measurements of groundwater level in 13 monitoring wells during a period of one year (Nov./2013 to Oct/2014). The neural network toolbox available in MATLAB version 7.1 (2010B) was used to develop the ANN models. Three layers feed-forward network with Log- sigmoid transfer function was used. The networks were trained using Levenberg-Marquradt back-propagation algorithm. The ANN modes are divided into two groups, each of four models. The input data of the first group include hydraulic heads, while, the input data of the second group include hydraulic heads and recharge rates. Based on results of this study it was found that; the best ANN model for predicting groundwater levels in the study area is obtained when the input data includes hydraulic heads and recharge rates of two successive months preceding the target month, the best structure of ANN model is of three layers feed-forward network type composes of two hidden layers, each of ten nodes, and the including of recharge rates as input data, beside the hydraulic heads has improved slightly the results.
Groundwater in arid and semi-arid regions, such as the studied area (Safwan Al-Zubair area, south of Iraq), is of specific meaning as a major source for domestic use and irrigation demand. There is a need to better understand the interactions between groundwater and surface water (Shatt Al-Basrah Canal). These interactions can negatively affect the quality of groundwater in this area, especially that the water of Shatt Al- Basrah Canal contains highly concentrated pollutants. The aim of the study is to investigate the temporal disparity of river-aquifer interactions and count the amount of river interchange among canal and aquifer. In this research, a new concept of paradigm will be advanced utilizing RIVER package of Groundwater River Paradigm (MODFLOW) for the simulation of river-aquifer interaction operations. Six monitoring wells are chosen to evaluate the preliminary and historical groundwater hydraulic heads for six months and then use all collected data in Modflow to execute the simulation of numerical modeling to assessment the interaction between surface water and groundwater. The amount of seepage out from the canal towards the aquifer was (64.99 m 3 /day) in wet season (winter season), as a result of the high levels of the surface water compared to the hydraulic heads of groundwater. The amount of seepage in dry season towards the aquifer is equal to (336.8 m 3 /day).
A linked simulation-optimization model for obtaining the optimum management of groundwater flow is presented in this research. (MODFLOW, 98) packages are used to simulate the flow of the groundwater system. This model is integrated with an optimization model which is based on the genetic algorithm (GA). Three management cases were undertaken by running the model with adopted calibrated parameters. In the first case found the optimum value of the objective function is (0.32947E+08 m3/year), in other words, the pumping rates could be raised to nine times the current pumping rates, with a highest decline in the hydraulic heads of groundwater compared with initial hydraulic heads reached to 6 cm. In a second case twenty six wells out of thirty five can be operated with "on/off" status associated with each well to obtain the maximum value of pumping rate. In third case is allowed to move a location of well anywhere within a user defined region of the model grid until the optimal location is reached. The optimum value of objective function in third case is (0.35539E+08 m3/year) with 8% increasing of the pumping rates compared with the first case. This is due to the random distribution of existing well locations.