Prediction Models to Control Aging Time in Red Wine.

Gonzalo Astray,Jesus Simal-Gandara,Juan Mejuto,Víctor Martínez-Martínez,Maria Alamo-Sanza,Ignacio Nevares

doi:10.3390/molecules24050826

Gonzalo Astray, Jesus Simal-Gandara + Show 4 more

Open Access

https://doi.org/10.3390/molecules24050826

Copy DOI

Abstract

A combination of physical-chemical analysis has been used to monitor the aging of red wines from D.O. Toro (Spain). The changes in the chemical composition of wines that occur over the aging time can be used to distinguish between wine samples collected after one, four, seven and ten months of aging. Different computational models were used to develop a good authenticity tool to certify wines. In this research, different models have been developed: Artificial Neural Network models (ANNs), Support Vector Machine (SVM) and Random Forest (RF) models. The results obtained for the ANN model developed with sigmoidal function in the output neuron and the RF model permit us to determine the aging time, with an average absolute percentage deviation below 1%, so it can be concluded that these two models have demonstrated their capacity to predict the age of wine.

Highlights

In the last decade, consumers have become interested in foods identified with a place of origin [1], and in their characteristics and quality [1,2]
There are different quality schemes under a geographical indication according to specific characteristics: (i) protected designation of origin (PDO), (ii) protected geographical indication (PGI) and (iii) geographical indication of spirit drinks and aromatized wines (GI) [8]
During the ageing process of the same red wine with alternative products+MOX, a series of process reactions take place as a result of the wine coming into contact with the wood [47]

Summary

Introduction

Consumers have become interested in foods identified with a place of origin [1], and in their characteristics and quality [1,2]. In the European Union (EU), wines produced in specified regions are clearly identified and controlled [7]. In this sense, there are different quality schemes under a geographical indication according to specific characteristics: (i) protected designation of origin (PDO), (ii) protected geographical indication (PGI) and (iii) geographical indication of spirit drinks and aromatized wines (GI) [8]. The use of these schemes impacts on market recognition and even results in higher sale prices For this reason, the improper use of these geographical indications can be injurious to producers and consumers [1]. South European countries (Spain among others) are involved in food authentication studies, for example in wines and foodstuffs registered as, among others, PDO [9]

Objectives

Methods

Results

Conclusion