Empirical mathematical models and artificial neural networks for the determination of alum doses for treatment of southern Australian surface waters

Abstract

The potential for predicting alum doses for surface waters from southern Australia based on physico-chemical parameters of the raw waters was studied. These parameters included dissolved organic carbon (DOC), absorbance at 254 nm, turbidity and alkalinity. Procedures used for assessing the predictability of alum dosing were empirical mathematical models and artificial neural networks. Alum doses determined by jar tests were selected on the basis of target values for settled and filtered turbidities, colour and residual aluminium. Regression equations which incorporated the parameters of DOC, UV absorbance (254 nm/cm), turbidity, alkalinity and pH gave correlation coefficients of greater than 0.9. These equations gave a high frequency of prediction within ±10 mg/L alum of actual doses. Similarly, 86% of alum doses predicted by artificial neural networks were within 10 mg/L of the actual doses. Although a good prediction of coagulant dosing was achieved, it is likely that the models generated are specific for the types of waters studied and the criteria for alum dose selection.