Integrated Artificial Neural Network Modeling and GIS for Identification of Important Factor on Groundwater Hydrochemistry (Fe-,Ca2+ and PO4 -3)

Background & Aims of the Study: Groundwater resources are a crucial component of theecosystem. Management and cleanup of contamination from groundwater resources requires along term strategy and a huge amount of investments. Artificial neural networks (ANN) andGeographic Information System (GIS) can be useful in determining management strategies. Toprotect these valuable resources, groundwater hydrochemistry (Fe-, Ca2+ and PO4-3) spatialdistribution is evaluated; also, the important parameters that affect their rate and spatialdistribution are identified.Materials and Methods: This study employed GIS technique and Modeling technique based onartificial neural network for identification and investigation of important factor on groundwaterhydrochemistry such as Fe-, Ca2+ and PO4-3. The case study is Ghareh-su basin of Golestanprovince of Iran. The maps of land use, soil, geology, population density, digital elevationmodel, distance from built-up areas, roads and rivers, cultivated land density and water table arethe parameters that used for running ANN model. Sensitivity analyses were also performed toidentify the effective parameters of ground water hydrochemistryResults: The results show that the concentration of the parameters around Gorgan and Kordkuycities, and areas where the cultivated land is denser, is high.Results indicated that the highest concentrations of these parameters were located around Gorganand Kordkuy cities and where the cultivated lands have a high density. The present contributionconfirms that a significant relation between the concentration of pollutants in groundwaterresources and different land uses/land covers is found. Soil type, geological structure and highgroundwater level in the north of Ghareh-su basin have a great impact on groundwater quality.Conclusion: These techniques have successfully implemented in groundwater hydrochemistrymapping of Ghareh-su basin.

Keywords:

Ground water protection , GIS , Ghareh-su , land use , land cover , Artificial Neural Network , Iran