Determine the Vulnerability of the Aquifer Using the Standard Drastic and Data-Based Methods (Case Study: Kochisfahan Aquifer)

The use of groundwater plays an important rule for agricultural and drinking water purposes in the north of Iran especially in Koochesfehan region. In these areas, the excessive use of chemical fertilizers, especially nitrogen based ones, beside the inadequacy in the treatment and release of urban and industrial wastewater are some of the most effective parameter in groundwater pollution, especially about the concentration of nitrate. Therefore, identification and mapping of vulnerable aquifer areas, i.e. areas where pollutants can be penetrated and discharged from the ground surface to the groundwater system, is an appropriate management tool for preventing the pollution of groundwater resources. In this study, with the purpose of identifying vulnerable aquifers and areas with high nitrate content as the main vulnerability areas, by using 7 variables the Drastic method and by using the Aller weighing criterion, vulnerability index of the region was estimated. Then, by comparing the vulnerability index and the amount of nitrate measured in the zoned area, the correlation between nitrate and Drastic vulnerability index was calculated. The results showed that the vulnerability of the Astaneh-Koushfahan plain aquifer is located in four areas: 56.16% of the plain has a low vulnerability, 51.29% has a low to moderate vulnerability, 28.46% has a moderate to high vulnerability, 67.1% is vulnerable. It is too much. The correlation between the Drastic (vulnerability) index and the concentration of nitrate was 80%, which confirmed that nitrate was the main cause of vulnerability in this the aquifer. So, finding a method for estimating the amount of nitrate in present and future in this area with high speed and precision was assumed as the goal of this study. The amoun of nitrate were estimated with four artificial intelligence artificial neural network, fuzzy model, support vector model and fuzzy-neural network. For this purpose, the seven Drastic variables data assumed as input parameters and the measured nitrate content in 30 different wells of the area were zoned by use of GIS software and divided into two categories of training and experimentation and they give as output parameters to all data-driven models. The results showed that all used artificial intelligence models give a good estimation of the amount of nitrate, but the neural network model had the best results, so that there was a correlation of 98% between computational nitrate and observation nitrate value. Finally, by choosing the model of the neural network as the superior model, it was tried to estimate the nitrate by decreasing the input parameters. The results showed that with 5 parameters of soil environment-unsaturated medium-saturated environment -water-hydraulic and eliminating two parameters of nutrition and topography, the correlation of estimated nitrate with the actual amount of measured nitrate is 0.90.