The high amount of Electrical Conductivity (EC) in the groundwater is one of the major negative Geo-environmental problems which has a considerable effect on the quality of drinking water. To address this challenging problem we proposed an intelligent Machine Learning (ML) based approach to predict EC in urban areas. We applied the deep learning technique as one of the most applicable ML techniques with high capabilities for intelligent predictions. Five different deep neural networks (Net 1 to Net 5) were developed in this study and their reliability to predict EC with an emphasis on different settings of inputs, features, functions, and the number of hidden layers was evaluated. The achieved results showed that deep neural networks can predict EC parameters using minimum and economic input parameters. Results showed parameters Cl and SO4 with a high range of correlation and pH with a low range of Pearson correlation properties are influential parameters to be used as the input of neural networks. Activation function Relu, optimization function Adam with a learning rate of 0.0005 and loss function Mean Squared Error with the minimum of two hidden dense layers from Keras laboratory of Tensor Flow developed an efficient and fast network to predict the EC parameter in urban areas. Maximum epochs for developed networks were defined up to 2000 iterations while epochs are reducible up to 200 to drive minimum loss function outcome. The maximum training and testing R2 for developed networks was 0.99 in both the training and testing parts.

The aim of this study is to determine the amount of quantitative and qualitative changes in groundwater in the Sarvestan plain in south of Fars province, which is one of the critical plains in Iran in terms of water resources. In this research, zoning maps of electrical conductivity of water in GIS were prepared and various hydrochemical diagrams were illustrated. Different quality parameters of water resources were compared according to the statistical data collected and the experiments performed at the beginning of the 8-year period of the research. Chemical analysis of water samples shows that the groundwater type of most of the studied wells at the beginning of the period (2013) has changed from Ca-Cl and Mg-Cl types to Na-Cl type at end of the time period (2020). Determining the trend of chemical changes shows that the diversity of water samples in terms of anions and cations in water with increasing salinity at the end of the period is less than the variety of samples at the beginning of the period. According to the results of chemical experiments, evaporation, crystallization, and weathering of rocks are the factors that control the composition of groundwater in the study area. This study shows increasing the salinity of groundwater in addition to decreasing precipitation and high water use for agricultural application, due to the type of geological formations, especially the presence of salt domes at groundwater inlets to the plain on the east side of the study area.

Water scarcity, its necessity in food production, and environmental protection in the world have forced human beings to seek new water sources. Nowadays, application of unconventional water resources (wastewater) has been proposed in countries facing the crisis of water resources shortage; however, a few studies have dealt with this issue. The present study has evaluated the changes in the elements of the soil, irrigated with wastewater. For so doing, an experiment has been conducted on a randomized complete block design with three replications. Soil samples have been collected from the studied regions at two depths of 0-30 cm and 30-60 cm and the studied parameters have included sodium, total calcium, magnesium, some acidity, and electrical conductivity of the soil. Three regions of study (namely no irrigation, irrigation with treated wastewater, and irrigation with river waters) have been taken into consideration. Results have shown increased calcium, magnesium, and pH of the effluent from Zabol Wastewater Treatment Plant compared to the control; however, electrical conductivity and chloride have decreased in wastewater-irrigated soil. The electrical conductivity in the surface layer of wastewater samples, treated with an amount of 2.25 (ds/m), has had the most significant difference to the control and other treatments. It can be concluded that wastewater increases some soil properties, contributing to its restoration.