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.
River engineers often analyze the overbank fl ows using subdivision techniques through the selection of assumed interface planes. A wrong selection of interface planes between the main channel and fl oodplain accounts for transfer of improper momentum, which inculcates error in estimation of discharge for compound channel section. Distribution of apparent shear stress between the main channel and fl oodplain gives an insight into the magnitude of momentum transfer based on which the discharge estimation using divided channel methods is decided. In the present study, experimental results of momentum transfer at various interface plains for straight and meandering compound channels are presented. Momentum transfer and boundary shear distribution are found to be dependent on the dimensionless parameters viz., overbank fl ow depth ratio, width ratio, sinuosity, and the orientation of the interfaces. The developed equation helps to predict the discharge carried by compound channels of different geometry and sinuosity. The present study indicates that for a straight compound channel, the horizontal division method provides better discharge results for low overbank fl ow depth and diagonal division method is good for higher overbank fl ow depths. The best discharge results for a meandering compound channel are obtained through diagonal division method for low overbank fl ow depths and vertical division method is good for higher overbank fl ow depths. The adequacies of the present results are verifi ed using present experimental data, and the data collected from the large channel facility (FCF) at Wallingford, UK. These methods agree well when applied to some natural river data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.