Hyperspectral imaging and machine learning for monitoring grapevine physiology

Following anecdotal evidence of unwanted ‘tropical’ character in red wines resulting from vineyard interventions and a subsequent yeast trial observing higher ‘red fruit’ character correlated with higher thiol concentrations, the role of polyfunctional thiols in commercial Australian red wines was investigated.
First, trials into the known tropical thiol modulation technique of foliar applications of sulfur and urea were conducted in parallel on Chardonnay and Shiraz.1 The Chardonnay wines showed expected results with elevated concentrations of 3-sulfanylhexanol (3-SH) and 3-sulfanylhexyl acetate (3-SHA), whereas the Shiraz wines lacked 3-SHA. Furthermore, the Shiraz wines were described as ‘drain’ (known as ‘reductive’ aroma character) during sensory evaluation although they did not contain thiols traditionally associated with ‘reductive’ thiols (H2S, methanethiol etc.).

Deciding to grow grapes in Oregon is complex issue due to our diverse geography, climate, and relatively short history of grape growing. For any potential grape grower, vineyard site selection is the single most important decision they will face.

Estimation of vineyard leaf area index (LAI) is an important aspect for the winegrowers. However, tracking and monitoring are difficult tasks due to time constraints. Satellite and unmanned aerial vehicle (UAV) imaging have become a practical monitoring method for LAI. Nevertheless, for a proper LAI determination, the image’s spatial resolution is a key factor, since low-resolution images are incapable of distinguishing between adjacent vines due to the large area covered in each pixel, this leads to misinterpretation or generalisation of vineyard information.

Proximal sensors are becoming widely used in precision viticulture, due to the quick, easy and non-invasive identification of soil spatial variability. The apparent soil electrical conductivity (ECa) is the main parameter measured by sensors, which is correlated to many factors, like soil water content, salinity, clay content and mineralogy, rock fragments, bulk density, and porosity.

As knowledge about the oenological potential of disease-tolerant grape varieties (PIWI) continues to grow and consumer demand for product safety and sustainable production increases, more governments worldwide are permitting the cultivation of these varieties [1].