Using Spatial Clustering in Forecasting Groundwater Quality Parameters by ANFIS

Groundwater is a major source of water supply for domestic, agricultural, and industrial uses; hence, its quality modeling is an important task in hydro-environmental studies. While many data-based models have been developed for this purpose, the performance of such data-based models can be drastically enhanced if they are based on temporal and spatial pre-processing. In this study, geostatistics tools (e.g., Co-Kriging), as spatial estimators, and self-organizing map (SOM), as a clustering technique, were employed in conjunction with Adaptive Neuro-Fuzzy Inference System (ANFIS) for the temporal forecasting of such quality parameters as electrical conductivity (EC) and total dissolved solids (TDS) of the groundwater in Ardabil Plain. Using the results thus obtained, the impact of spatial data clustering was also investigated on the same parameters. The results showed that, if propoer input data are selected, the proposed spatial clustering technique is capable of imporving groundwater quality forecasts made by ANFIS.