Hyperspectral imaging and machine learning for monitoring grapevine physiology

Context and purpose of the study ‐ Recently early defoliation (ED) has been tested in several high‐ yielding grapevine varieties and sites aiming at reducing cluster compactness and hence, regulating yield and susceptibility to botrytis bunch rot infection. The reported results have been generally positive, encouraging growers to use this canopy management technique as an alternative for replacing the conventional time‐consuming cluster thinning and, simultaneously, as a sustainable practice to reduce the use of fungicides. However, ED increases berry sunburn risks and/or can induce carry‐over effects on vigor and node fruitfulness as shown in the two case studies reported in this work.

Aim: Pests have a high impact on yield and grape quality in viticulture. An objective and rapid detection of pests under field conditions is needed. New sensing technologies and artificial intelligence could be used for pests detection in digital viticulture. The aim of this work was to apply computer vision and deep learning techniques for automatic detection of spider mite symptoms in grapevine under field conditions. 

Since the mid-1980s, several surveys have been carried out in La Rioja to search for populations of the sylvestris grapevine subspecies (Vitis vinifera L. subsp. sylvestris Gmelin). The banks of the Ebro River and its tributaries (Alhama, Cidacos, Leza, Iregua, Najerilla, Oja and Tirón rivers), as well as the surrounding vegetation of their valleys have been covered. So far, all the populations found are alluvial, forming part of the riparian vegetation of the Najerilla (the first reported population in La Rioja [1]), Iregua, and the vicinity of Oja valleys.

Tannin composition is an important attribute in red wine quality, and it is therefore critical to understand the factors influencing tannin extraction during alcoholic fermentation. Tannins contribute to the mouthfeel of wines, but they also form pigmented polymers...

Grapevine rootstocks provide protection against environmental biotic and abiotic stresses. Nitrogen (N) and iron (Fe) are growth-limiting factors in many crop plants due to their effects on the chlorophyll and photosynthetic characteristics. Iron nutrition of plants can be significantly affected by different nitrogen forms through altering the uptake ratio of cations and anions, and changing rhizosphere pH. The aim of this study was to investigate the response mechanisms of grapevine rootstocks due to the interaction between different nitrogen forms and iron uptake.