Prediction of Water Quality Index Using Neuro Fuzzy Inference System

The groundwater near mines is contaminated heavily as regards acidity, alkalinity, toxicity, heavy mineral, and microbes. During rainy season, the mines are filled with the water which contaminates the groundwater and gradually disperses by percolating through the soil into urban area, making the water unsuitable for use. In addition, fertilizers used for agricultural purpose affect pH and nitrate content of groundwater. Hence, evaluation of WQI of groundwater is extremely important in urban areas close to mines to prepare for make remedial measures. To this end, the present study proposes an efficient methodology such as adaptive network fuzzy inference system (ANFIS) for the prediction of water quality. The parameters used to assess water quality are usually correlated and this makes an assessment unreasonable. Therefore, the parameters are uncorrelated using principal component analysis with varimax rotation. The uncorrelated parameters values are fuzzified to take into account uncertainty and impreciseness during data collection and experimentation. An efficient rule base and optimal distribution of membership function is constructed from the hybrid learning algorithm of ANFIS. The model performed quite satisfactorily with the actual and predicted water quality. The model can also be used for estimating water quality on-line, but the accuracy of the model depends upon the proper training and selection of parameters.