Hyperspectral imaging and machine learning for monitoring grapevine physiology

The knowledge of the influence of soil conditions on the effects that different plant densities provoke in the agronomic grapevine behaviour becomes very interesting since it allows to focus the vineyard management on the optimization of the natural, hydric and human resources.

Plants in their natural environment are in continuous interaction with large numbers of potentially pathogenic and beneficial microorganisms. Depending on the microbe, plants have evolved a variety of resistance mechanisms that can be constitutively expressed or induced. Phytoalexins, which are biocidal compounds of low to medium molecular weight synthesized by and accumulated in plants as a response to stress, take part in this intricate defense system.1,2
One of the limitations of our knowledge of phytoalexins is the difficulty of analyzing their spatial responsiveness occurring during plant- pathogen interactions under natural conditions.

Enzymatic browning (BE) of must is caused by polyphenol oxidases (PPOs), tyrosinase and laccase. Both PPOs can oxidize diphenols such as hydroxycinnamic acids (HA) to quinones, which can later polymerize to form melanins [1], which are responsible of BE in white wines and of oxidasic haze in red wines. SO₂ is the main tool used to protect must from BE thanks to its capacity to inhibit PPOs [2]. However, the current trend in winemaking is to reduce and even eliminate this unfriendly additive. Among the different possible alternatives for protecting must against BE, the inoculation with a selected Metschnikowia pulcherrima MP1 is without any doubt one of the most promising ones.

Grapevine is one of the world’s most important cultivated plants, domesticated from the wild vine over 11,000 years ago. The fungi associated with it are doubtless as old as the plant itself. Despite their co-evolution with the vine over the centuries, it was only with the invention of the microscope in the seventeenth century that fungi started to be recognised.

Two treatments were studied in vines of cv. Tempranillo blanco (Vitis vinifera L.) during the 2012-2018 period in an experimental plot located in Rincón de Soto (La Rioja, Spain). Rainfed treatment (R0) was compared with respect to an irrigation treatment (R2) equivalent to 30% of the crop evapotranspiration (ET0) from fruitset to harvest phenological stages. Pre-veraison irrigation ranged from 43 (2014) to 66 mm/m2 (2018) while post-veraison irrigation ranged from 37 (2017) to 115 mm/m2 (2012).The normalized difference vegetation index (NDVI) was assessed by measures of reflectance, nutrients were determined by analysis of petioles sampled at veraison, grape production was determined at harvest as well as renewable wood weight was assessed at pruning time.