Estimating the spatial distribution ofgroundwater quality parameters of Kashan plain with integration method of Geostatistics - Artificial Neural Network Optimized by Genetic-Algorithm

ABSTRACT: In recent years, several statistical, mathematical and computer simulation methods to estimate quality parameters of aquifer water are taken into consideration. In monitoring water quality in the aquifer, the quality of natural and artificial factors is thoroughly considered. Groundwater monitoring can be used for characterization of geological and hydro-geological information such as aquifers, distributed Hydro load in time and space, the direction of underground water flows, water quality and quantity of contaminants and contaminant source characteristics can be achieved. As quality parameters of groundwater in plains is observed as spots on the extraction wells it is necessary that the resultant spotty extraction data to be generalized to the area. There are different algorithms for spatial interpolation of the geometric and some of them are based on geostatistical methods. In this study, the combination of statistical methods and artificial neural networks has been used in order to estimate the quality parameters of spatial distribution of sodium, calcium and magnesium Plain Groundwater KASHAN more accurately. First we analyze the interpolation and geostatistic method and then the use of artificial neural networks to optimize the results of geostatistical methods have been studied. Results show accurate performance of the optimized hybrid approach using genetic algorithm to estimate parameters of quality under study so that the amounts of sodium, calcium and magnesium account were estimated, with coefficients 99 and 99 for 98 % respectively.