Groundwater quality modeling using self-organizing map (SOM) and geographic information system (GIS) on the Caspian southern coasts

Groundwater is the main source for water provision in the arid and semi-arid areas such as Iran. The groundwater quality was simulated by using a hybrid model integrating a Self-Organizing Map (SOM) and geographic information system (GIS). SOM and GIS were used as pre-processing and post-processing tools in the Mazandaran Plain. Further, the Ground Water Quality Index (GWQI) and its effective factors were estimated by using digital maps and the secondary data. NeuroSolutions software was used for simulating the groundwater quality. To do this, a model was trained and optimized in the SOM and then the optimized model was tested. In the next step, the performance of SOM in groundwater quality simulation was confirmed (test stage,Rsqr=0.8, and MSE=0.008). Then, the digital maps of the SOM inputs were converted to raster format in GIS. In the last step, a raster layer was generated by combining the model input layers which comprised the model inputs values. The tested SOM was used to simulate GWQI in the sites without the secondary data of the groundwater quality. Finally, the groundwater quality map was generated by coupling the results of SOM estimations and GIS capabilities. The results revealed that the coupling of SOM and GIS has high performance in the simulation of the groundwater quality. According to the results, a limited area of the studied plain has groundwater resources with low quality (GWQI>0.04). Therefore, that will be a threat to the life of humans, animals, and vegetative species. Therefore, it is necessary to plan for managing the groundwater quality in the Mazandaran plain.