Hyperspectral imaging and machine learning for monitoring grapevine physiology

Vineyard exposure to smoke can lead to grapes and wine which exhibit objectionable smoky and ashy aromas and flavours, more commonly known as ‘smoke taint’ [1, 2]. In the last decade, significant bushfires have occurred around the world, including near wine regions in Australia, Canada, South Africa and the USA, as a consequence of the warmer, drier conditions associated with climate change. Considerable research has subsequently been undertaken to determine the chemical, sensory and physiological consequences of grapevine exposure to smoke. The sensory attributes associated with smoke-tainted wine have been linked to the presence of several smoke-derived volatile phenols, such as guaiacols, syringols and cresols [2].

There are currently enzyme preparations on the market with specific protease activities capable of degrading unstable must proteins and preventing turbidity in white and rosé wines. The main drawback is the need to heat the must at 75ºc for 1-2 minutes to denature the proteins and facilitate enzyme action.

Grape flavour management in the vineyard requires knowledge of the derivation of individual flavour and aroma characteristics and the effects that different concentrations and interactions between these compounds have on flavour potential.

The wine industry is increasing the demand for indigenous yeasts adapted to the terroir to produce unique wines that reflect the distinctive characteristics of each region. In our group, we have identified and characterized 60 native yeast strains isolated from a vineyard in Maldonado-Uruguay, in which three strains stood out: Saccharomyces cerevisiae T193FS, Saturnispora diversa T191FS, and Starmerella bacillaris T193MS. Their oenological potential was evaluated at a semi-pilot scale in Tannat must vinification in the wine cellar to have a more precise and representative evaluation of the final product.

Context and purpose of the study. Intra-varietal variability for key physiological and oenologically important traits can be exploit in viticulture following the consistently higher environmental pressure driven by climate change.