How AI and MATLAB are Helping Winegrowers Analyse Bushfire Smoke Contamination

Over the last decade, the occurrence of bushfires has worsened. Australia has experienced one of the longest and most severe bushfire events in recorded history, gravely affecting wine regions. From the recent bushfire event, Adelaide Hills, an iconic wine region, has lost more than a third of its grapevine plantations. Smoke produced from bushfires can pollute vineyards by contaminating berries with unsavoury compounds, known as smoke taint, that are later passed to the wine. Wines tainted by smoke present sensorial aromas described as ash, smoky, burnt and medicinal, which can spoil an entire vintage. At present, there are no available tools for winegrowers to assess smoke contamination and make an informed decision on what amelioration measures can be implemented. The Digital Agriculture, Food and Wine group at the University of Melbourne has devised short- and long-range remote sensing techniques and e-noses coupled with Artificial Intelligence using MATLAB to obtain Machine Learning models to assess smoke contamination in grapevines and smoke taint in final wines.