Artificial neural network model as a potential alternative for groundwater halogenated hydrocarbon pollution forecasting

The paper evaluates the prospect of artificial neural network (ANN) simulation over mathematical modeling in estimating volatile organic compounds pollutants in groundwater. Momentum-Adaptive Back-Propagation (MABP) ANN model with quick propagation as training algorithm has been used to forecast halogenated hydrocarbons pollution by contrasting conventional ions. The accuracy, generalization ability and reliability of the model are verified by laboratory data. This model is trained with 26 samples of laboratory data and made prediction on dichloromethane of another 20 samples which can be used to represent halogenated hydrocarbons pollution. The proposed ANN model has surfaced as a simpler and more accurate alternative to the numerical method techniques. ANN can be used as a guide for investigation of groundwater halogenated hydrocarbons pollutions. It further projects a guideline on sampling distribution.