Macrowine 2021
IVES 9 IVES Conference Series 9 Neural networks and ft-ir spectroscopy for the discrimination of single varietal and blended wines. A preliminary study.

Neural networks and ft-ir spectroscopy for the discrimination of single varietal and blended wines. A preliminary study.

Abstract

Blending wines from different grape varieties is often used in order to increase wine complexity and balance. Due to their popularity, several types of blends such as the Bordeaux blend, are protected by PDO legislation. In the case of monovarietal wines blending is forbidden, however there is no method to authenticate their status, and for this reason adulteration can are difficult to identify. Fourier Transform Infrared Spectroscopy (FT-IR) has proven successful for the discrimination of wines based on several parameters such as geographical origin and type of aging[1], while the use of Neural Networks is now used more often for the development of prediction models. FT-IR spectroscopy coupled with Neural Networks have been used to develop a prediction model for the discrimination of single varietal and blended wines. Generalized RSquare for the training set was 0,9011 and 0,689 for the validation set, while the -Loglikelihood was 3,918 for the training and 0,111 for the validation set. The misclassified rate was 0,03 for the training set and 0,11 for the validation set, showing very good potential for the use of IR spectroscopy for the authentication of single varietal and blended wines.

DOI:

Publication date: September 10, 2021

Issue: Macrowine 2021

Type: Article

Authors

Marianthi Basalekou

University of West Attica,Christos, PAPPAS, Agricultural University of Athens Petros, TARANTILIS, Agricultural University of Athens Anna, Georgoulaki, University of West Attica Anna, STEFOU, University of West Attica

Contact the author

Keywords

ftir, wine, blend, neural networks

Citation

Related articles…

For a phenomenology of terroir. A consumers’ perspective

This study investigates the notion of terroir by applying a phenomenological approach, focusing on the subjective experience of consumers. We will consider how terroir is described by consumers in order to gauge their subjective viewpoint and understand their way of describing and defining this spatiality.

Read More

Drought tolerance of varieties in semi-arid areas: can the behavior of Tempranillo be improved by varieties of its own lineage?

Tempranillo is the most widely grown red grapevine variety in Spain, currently representing 42% of the total number of red varieties and 21% of the total vineyard area. Due to the economic importance that this variety represents in Spanish viticulture, in some areas where it is traditionally grown, there is a special concern about the viability of the future growing of this variety is being compromised by the climate change effects.

Read More

The origin and the discovery of “terroir”

Le mot “terroir” dérive du latin “terra”, mais déjà les Romains l’indiquaient comme “locus” ou”loci”, c’est-à-dire un lieu ayant le “genius”destiné à la production d’un produit d’excellente qualité.

Read More

Yeast derivatives: an innovative approach to produce Oenococcus oeni under biofilm form?

The malolactic fermentation can occur naturally or be induced by inoculation of selected bacterial strains, most commonly of Oenococcus oeni.

Read More

Comprehensive two-dimensional gas chromatography coupled with Tof-MS, a powerful tool for analysis of the volatomes of grapes and wines

Comprehensive two-dimensional gas chromatography (GCxGC) has emerged as a powerful analytical technique for unraveling the volatile composition of complex matrices. This work will present three applications of GCxGC Tof-MS to the oenological field, aimed to identify novel biomarkers to be used in the quality control process of the wine industry. Comprehensive mapping of volatile compounds was conducted in a large sample of 70 sparkling wines, produced by 48 different wineries across 6 vintages and representative of the two main production areas for premium Italian sparkling wines (Franciacorta (FC) and Trentodoc (TN)), using HS-SPME followed by GCxGC-Tof-MS and multivariate analysis. Selection and identification of 196 putative biomarkers allowed clear separation of sparkling wines from FC and TN.

Read More