Hyperspectral imaging and machine learning for monitoring grapevine physiology

In a climate change context, the management of Mediterranean vineyards should be adapted to the new environmental conditions. Predictive models underline that in the future the most of the Mediterranean vineyard regions is expected to experience further warming events producing challenges in ripening balanced fruit. It is already registered that in warm and dry summers, the ripening process is faster and the balance between phenolic and technological (sugar) maturity may not be the desirable. This study investigates the use of specific inactivated yeast derivatives sprayed on the entire canopies of field grown cv Muscat Hamburg vines.

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.

The use of pesticides for vine growing is responsible for generating an important volume of wastewater. In 2009, 13 processes were authorized for wastewater treatment but they are expensive and the toxicological impact of the secondary metabolites that are formed is not clearly established. Recently photodecomposition processes have been studied and proved an effectiveness to degrade pesticides and to modify their structures (Maheswari et al., 2010, Lassale et al., 2014). In this field, Pulsed Light (PL) seems to be an interesting and efficient process (Baranda et al., 2017). Therefore, the aim of this work was to investigate the PL technology as a new process for the degradation of pesticides.

In plants, stress due to nutrient deficiency can significantly impair their development and productivity.

Climate is one of the main components that defines the development and behavior of the plant, conditioning the health status and the final quality of the grapes. In temperate coastal climates such as in Uruguay (latitude 35° S, longitude 55° O), precipitations during the growing season present high interannual variability, with a average of 100 mm per month. This variability means that plants must adapt to conditions from one year to the next.