Hyperspectral imaging and machine learning for monitoring grapevine physiology

Context and purpose of the study ‐ An advancement of grapevine phenological development has been observed worldwide in the last two decades. In South Australia this phenomenon is even more accentuated since grapevine is often grown in a hot climate. The main consequences are earlier harvests at higher sugar levels which also result in more alcoholic wines. These are deemed undesirable for the Australian wine industry with consumer preferences shifting towards lower alcohol wines. Vineyard practices can be implemented to control and delay ripening. Amongst them, apical late leaf removal has been successfully applied in Europe to delay ripening by up to two weeks in Sangiovese, Aglianico and Riesling. In those studies, no negative effects were observed on grape colour, phenolics and on the carbohydrate storage capacity of the vines. To date, this technique has not been studied in Australia. In this study late leaf removal, apical to the bunch zone was applied to the variety Semillon for four seasons and compared to an untreated control.

Mild to moderate and timely water deficit is desirable in grape production to optimize fruit quality for winemaking. It is crucial to develop robust and rapid approaches to assess grapevine water stress for scheduling deficit irrigation. Hyperspectral imaging (HSI) has the potential to detect changes in leaf water status, but the robustness and accuracy are restricted in field applications.

In the current context of market competition and consumption evolution, it is necessary to produce wines of a genuine typicity. The Terroir represents an unique and irreproducible inheritance that can be valorized through the origin and the sensory characteristics of the wines.

Avec l’accroissement des surfaces viticoles conduites en Bio, la question de l’impact de la présence de résidus de cuivre (seul anti fongique autorisé dans l’UE dans ce cadre Règlementaire) sur le déroulement des fermentations et sur les qualités œnologiques et organoleptiques des vins s’est révélée de plus en plus cruciale.

Over the past two years, the AWRI has received 69 wine samples suspected of being affected by mousy off-flavour. The character has been mostly observed in white wines.