Verification of the geological origin of bottled mineral water using artificial neural networks

As a first step towards objective and cost-efficient verification of the geographical origin of commercially sold mineral water, we determined up to what extent the chemical composition of mineral water can be linked to the geology of the local water source. For this purpose, a dataset consisting of 145 European mineral water samples from a known geology was analysed using counter-propagation artificial neural networks (CP-ANNs) with supervised learning algorithm. The models were tested for recall ability (RA) and validated with a leave-one-out cross validation (LOO-CV). timal model shows 85% and 65% correct predictions on RA and on LOO-CV, respectively, indicating a substantial success to correctly predict the geology of the mineral water samples. Results further show that using the proper lithological classification scheme largely determines the success of the prediction, whereas inclusion of the calculated saturation indices of different solutes as additional variables in the data appeared to have negligible effect on the predictive power of the model.