Experimental investigation of trihalomethane formation and its modeling in drinking waters

This research developed models using multiple linear regression analysis for the prediction of trihalomethane formation in coagulated Istanbul drinking water sources. The power-law model (model 1), using only ΔUV₂₇₂ as the designed parameter, proved the best model to describe the formation of trihalomethane. The other model (model 2), included pH, total organic carbon, chlorine dosages, ultraviolet absorbance at 254 nm (UV254), specific ultraviolet absorbance (SUVA) and differential absorbance at 272 nm (ΔUV₂₇₂). The root-meansquare error (RMSE), normalization mean square error (NMSE), regression coefficient (R²) and index of agreement (IA) were used as statistical variables to evaluate the model performance. The better prediction results were obtained by model 1 for root-mean-square error, normalization mean square error, R² and index of agreement as 9.14, 0.015, 0.95 and 0.99, respectively.