Terroir 2020 banner
IVES 9 IVES Conference Series 9 International Terroir Conferences 9 Terroir 2020 9 History and innovation of terroir 9 How geographical origin and vineyard management influence cv. Cabernet-Sauvignon in Chile – Machine learning based quality prediction

How geographical origin and vineyard management influence cv. Cabernet-Sauvignon in Chile – Machine learning based quality prediction

Abstract

Aims: The aims of this study were to i) characterize the impact of geographical origin and viticulture treatments on Chilean Cabernet-Sauvignon, and ii) develop machine learning models to predict its quality. 

Methods and Results: 100 vineyard plots representing the typical percentage distribution of geographical and viticulture impact factors on Chilean Cabernet-Sauvignon were monitored across two seasons, 2018 and 2019. Chemical analysis of grapes and wines included the quantification of phenolic compounds by liquid chromatography and UV-vis spectral measurements, aroma compounds by gas chromatography mass spectrometry (GC/MS), and maturity parameters. Spearman correlation and Principal component analysis (PCA) identified correlations of several non-volatile and volatile compounds with quality, mainly by means of their anthocyanins, flavonols, flavan‑3‑ols, total tannins and hydroxycinnamic acids. Furthermore by trans-2-hexenol, trans-3-hexenol, hexanal, 2-isobutyl-3-methoxypyrazine (IBMP), yeast assimilable nitrogen (YAN), total soluble solids and acidity. Experimental winemaking of 600 kg per plot followed a standardized procedure, and the wines were analyzed by an expert quality rating. A sensory quality profiling for the wines was performed through a Napping Ultra Flash Profile (UFP). It revealed the distinction of three different quality levels by mainly mouthfeel attributes, and fruity and green aromas. However, neither the observed correlations of chemical analysis and sensory quality ratings, nor origin or viticulture treatment could fully explain quality. Different clustering methods, namely k-means, k-medioids and spectral clustering were evaluated in order to find categories given by the chemical analysis data itself as unsupervised machine learning. Spectral clustering led to optimum results, and independently of sample origin and viticulture traits, quality ratings were characterized to be significantly different across the clusters allowing their interpretation as quality categories. 

Conclusions: 

Chilean Cabernet-Sauvignon quality is associated with chemical quality markers known for this variety in Australia and California, including phenolic compounds, C6 alcohols and aldehydes, IBMP, maturity parameters and YAN. However, evaluation of sensory quality is fairly subjective and viticulture treatments in practical application contain interdependency, therefore it is challenging to establish supervised models involving this data. The application of unsupervised spectral clustering is proposed as an objective quality classification approach, which can be trained using supervised models for predictive purposes.

Significance and Impact of the Study: There is a high industrial need for objective quality classification. For the first time chemical quality markers for Chilean Cabernet-Sauvignon were determined, and an unsupervised machine learning approach based on these markers could be proposed for objective quality classification.

DOI:

Publication date: March 19, 2021

Issue: Terroir 2020

Type: Video

Authors

Doreen Schober1*, Martin Legues1,2, Hugo Guidez3, Jose Carlos Caris Maldonado1, Sebastian Vargas1,  Alvaro Gonzalez Rojas1

1Center for Research and Innovation (CRI), Viña Concha y Toro, Ruta k-650 km 10, Pencahue, Región de Maule, Chile
2Pontificia Universidad Católica de Chile, Vicuña Mackenna 4860, Macul, Región Metropolitana, Santiago, Chile
3Institut National Supérieur des Sciences Agronomiques, Agroalimentaires, Horticoles et du Paysage, Agrocampus Ouest Campus d´Angers, France

Contact the author

Keywords

Cabernet-Sauvignon, spectral clustering, quality, terroir, vineyard management

Tags

IVES Conference Series | Terroir 2020

Citation

Related articles…

Barrels ad-hoc: Spanish oak wood classification by NIRs 

The wooden barrel is a key factor in enology, since wine chemical composition and sensory properties changes significantly in contact with the barrel[1]. Today’s highly competitive market constantly demands new differentiated products and wineries search innovations continuously.
Wood selection is crucial: barrels stability to keep constant their contribution and the result on products, and additional and differentiated wood contributions to impact their new products. Oak wood selection has traditionally been carried out using parameters such as specie, location and grain, however, it goes one step further nowadays. Large cooperage work with non-destructive techniques that allow classifying oak wood quickly and easily according to their organoleptic contribution[2].

Differentiation and characterization of Spanish fortified wines with protected designation of origin based on volatiles using multivariate approaches

Spain is one of the main producers of high-quality fortified wines. Particularly some of them elaborated in Andalusia have acquired a great prestige for being unique due to their production in a specific geographical area with traditional methods, the grape variety used, the climate and the soil. Such is their distinguishing feature achieved that they have been protected by the European Union with the indication “Protected Designation of Origin” (PDO). Thus, there are four PDO of fortified wines in Andalucía (‘Condado de Huelva’, ‘Jerez Xérès Sherry’, ‘Manzanilla Sanlúcar de Barrameda’, and ‘Montilla-Moriles’). Furthermore, within each PDO,there are different categories according to their particular characteristics and winemaking conditions such as the aging process.

Highlighting the several chemical situations of Dimethyl sulfide in wine

Dimethyl sulfide (DMS) is a compound that accumulate in wine for the early years of ageing 1. During this stage, which is often carried out in the bottle, the environmental conditions are conducive to the release of DMS from its precursors, already present in grapes2

Characterization of berry softening and sugar accumulation dynamics in a slow-ripening genotype and its response to abscisic acid treatments

In the current viticultural context, global warming leads to advanced and possibly accelerated ripening which can alter the balance among desirable grape quality traits sought for winemaking. Evaluation of genetic material that displays delayed and/or slower ripening could uncover a potential “slow ripening” trait for incorporation into commercial varieties through breeding. In this study, we evaluated a white-fruited selection discovered in the Grape Breeding and Genetics program at E. & J. Gallo Winery that displayed an unusual ripening pattern compared to standard varieties. Vines of the slow-ripening selection did not differ in their visual appearance, water status or gas exchange characteristics compared to vines of its normal-ripening sibling.

Landscapes of the wine: the four seasons of herault

Les paysages participent à l’identité des vins de l’Hérault, avec une grande richesse de diversité. Leur observation, au travers des quatre saisons, s’appuie sur deux dimensions primordiales : la genèse de leur construction par l’homme et l’esthétique. L’hiver est la saison la plus favorable au décryptage de ce vignoble étagé, du littoral méditerranéen aux premières pentes du Massif Central; il permet de lire l’histoire des stratégies viticoles des vignerons. Les autres saisons sensibilisent plus à la beauté de vignobles dans des écrins de végétation typiquement méditerranéenne. La multiplicité des pratiques culturales et des cépages contribue à cet attrait. L’incitation au parcours, en toute saison, est très forte grâce au réseau des routes et des chemins de vigne.