Application of artificial neural networks coupled to UV-VIS-NIR spectroscopy for the rapid quantification of wine compounds in aqueous mixtures

Abstract

Ultraviolet-visible (UV-VIS) and near-infrared (NIR) spectroscopy coupled to artificial neural networks (ANNs) was used as a non-destructive technique to quantify ethanol, glucose, glycerol, tartaric acid, malic acid, acetic acid and lactic acid in aqueous mixtures. Spectral data were obtained for 152 samples. Differing pre-treatments were applied to the spectra and ANN models were obtained using raw and pre-treated data to evaluate several spectral wavelength groupings and ANN training conditions. Feasible calibration models were obtained for ethanol, malic acid and tartaric acid. To validate the process, 120 new samples were measured using the best ANN models. The determination coefficients for the three compounds using this validation set were above 0.9. The results showed the importance of good parameter selection when training the ANN to obtain reliable models. Coupling UV-VIS-NIR spectroscopy to ANN could provide an alternative to conventional chemical methods for determining ethanol, tartaric acid and malic acid in wines.