Digital Smoke Taint Detection in Pinot Grigio Wines Using an E-Nose and Machine Learning Algorithms Following Treatment with Activated Carbon and a Cleaving Enzyme

The incidence and intensity of bushfires is increasing due to climate change, resulting in a greater risk smoke taint development wine. In this study, smoke-tainted non-smoke-tainted wines were subjected treatments using activated carbon with/without the addition cleaving enzyme treatment hydrolyze glycoconjugates. Chemical measurements volatile aroma compounds assessed for each treatment, with two amelioration exhibiting lower mean values positive ‘fruit’ aromas. Furthermore, low-cost electronic nose (e-nose) was used assess wines. A machine learning model based on artificial neural networks (ANN) developed e-nose outputs from unsmoked control wine, wine plus samples as inputs classify according treatment. displayed high overall accuracy 98% classifying readings, illustrating it may be rapid, cost-effective tool winemakers effectiveness by use enzyme. coupled found effective ameliorating help delay resurgence aromas following aging hydrolysis