Hyperspectral imaging and machine learning for monitoring grapevine physiology

Bud death due to cold damage is a recurrent and major economic issue with Vitis vinifera L. in the Northeastern U.S. winegrowing regions. Primary buds – and sometimes secondary and tertiary buds – are often damaged by fluctuating temperatures in the winter and early spring. To maintain balanced vegetative and reproductive growth of a vine, pruning practices need to be adjusted to account for bud damage. Conventional bud damage assessment requires growers to sample canes/spurs, cut nodes with a razor blade, and then visually assess bud damage. This process is laborious and becomes a major barrier for damage-compensated pruning decision-making, leading to too few live buds per vine and the associated excessive vigor and low yield that result. The overarching goal of this study was to develop an active thermographic system for non-destructive detection of bud damage in the vineyard.

The “Anjou Terroirs” programme aims at bringing the necessary scientific basis for a ratio­nal and reasoned exploitation of the technical itinerary of the terroir. The scale study is 1/12500. For the mapping, many parameters, such as the granulometry or the depth of soil are observed to each point of caracterisation.

High-power ultrasounds have been related to an accelerated aging of wines, an effect that has been associated to the formation of radical species caused by the cavitation phenomenon [1]. This phenomenon consists of the formation of bubbles in the liquid medium that, when they collapse, cause high-pressure hot spots and temperatures of up to 4800 k [2], notably increasing the reactivity in the medium.

The strategy of single berry phenotyping is a recently rediscovered research tool that has gained great attention. The latest studies have indicated that previous physiological models based on pooling asynchronous populations of berries provided biased or blurred information on berry development key players. The possibility of monitoring and sampling single synchronized berries to study their development sequentially has opened new lines of research aimed at unraveling the genes that regulate grapevine fruit development. This study aimed to decipher the gene pathways responsible for the activation/deactivation of physiological processes involved in the green phase of growth, the onset of ripening, and the second growth phase.

Wine viticulture, being firmly linked to the vine-terroir relationship, has always encountered significant bottlenecks to genetic innovation. Nonetheless, the development of new breeding strategies leading to the selection of stress resilient genotypes is urgent, especially in viticulture, where it would allow reducing the use of chemical treatments adopted to control fungal diseases. Genome editing represents an extremely promising breeding technique. Unfortunately, the well-known recalcitrance of several wine grape cultivars to in vitro regeneration strongly limits the exploitation of this approach, which to our knowledge has so far been developed on table grape genotypes with high regeneration potential.