Hyperspectral imaging and machine learning for monitoring grapevine physiology

Climate change is introducing a high variability on grape ripening, causing uncertainty, excessive spending on pesticides and eventually frustrating results in terms of the quality of the vintage, with the increasingly frequent appearance of aromatic problems associated with overripeness, raisining and greenness, which sometimes only appear in bottled wines.

Most grape scion cultivars grown around the world are derived from a single species, Vitis vinifera. Yet, the proportion of interspecific hybrids is increasing for a variety of reasons, including resistance to abiotic stresses such as low temperatures; societal, economic and environmental pressures to reduce pesticide usage; and to add a greater range of flavors to new table grape cultivars.

Seven plots located in the commune of Montigny-lès-Arsures (Jura, 39), planted with grapevine varieties Trousseau and Savagnin, were chosen for a study of soil pits and a distribution of major and trace chemical elements in soils and wines. It was shown that the mineral matrix of the soil reflects the geological substratum and the sub-surface alteration process, while the organic soil matrix depends on agro-viticultural practices.

Astringency is an important red wine quality attribute, which can be measured both chemically and sensorially. The use of tannin activity shows potential as a valuable chemical measurement in understanding red wine mouthfeel properties such as astringency and bitterness, which is also affected by tannin structural factors, in addition to matrix effects. Tannin activity is defined as the enthalpy of interaction between tannins and a hydrophobic surface. Studies involving tannin activity have been performed since the early 2010’s, but chemosensory studies used to evaluate how structure-activity relationships change across multiple, consecutive vintages are limited. The aim of this study is to investigate how tannin activity may be linked to red wine mouthfeel, and how all these variables may change according to wine age.

Characterize taste and mouthfeel properties of grapes elicited by the phenolic fraction (PF) of grape berries and establish relationships with chemical variables. METHODS: As many as 31 diverse grape lots of Tempranillo Tinto and Garnacha Tinta from three different regions were harvested. Grapes were destemmed and macerated in 15% of ethanol for one week and extracts were submitted to solid phase extraction. The recovered polyphenolic fraction was reconstituted in wine model and characterized by a panel of 21 wine experts employing a list of 23 taste and mouthfeel-related attributes following a rate-k-attributes methodology. RESULTS: Six significant attributes among the 31 samples differed based on ANOVA results: “dry”, “coarse”, “bitter”, “dry on tongue”, “sticky” and “watery”. PCA with VARIMAX algorithm was calculated.