Assessment of Smoke Contamination in Grapevine Berries and Taint in Wines Due to Bushfires Using a Low-Cost E-Nose and an Artificial Intelligence Approach

Abstract

Bushfires are increasing in number and intensity due to climate change. A newly developed low-cost electronic nose (e-nose) was tested on wines made from grapevines exposed to smoke in field trials. E-nose readings were obtained from wines from five experimental treatments: (i) low-density smoke exposure (LS), (ii) high-density smoke exposure (HS), (iii) high-density smoke exposure with in-canopy misting (HSM), and two controls: (iv) control (C; no smoke treatment) and (v) control with in-canopy misting (CM; no smoke treatment). These e-nose readings were used as inputs for machine learning algorithms to obtain a classification model, with treatments as targets and seven neurons, with 97% accuracy in the classification of 300 samples into treatments as targets (Model 1). Models 2 to 4 used 10 neurons, with 20 glycoconjugates and 10 volatile phenols as targets, measured: in berries one hour after smoke (Model 2; R = 0.98; R2 = 0.95; b = 0.97); in berries at harvest (Model 3; R = 0.99; R2 = 0.97; b = 0.96); in wines (Model 4; R = 0.99; R2 = 0.98; b = 0.98). Model 5 was based on the intensity of 12 wine descriptors determined via a consumer sensory test (Model 5; R = 0.98; R2 = 0.96; b = 0.97). These models could be used by winemakers to assess near real-time smoke contamination levels and to implement amelioration strategies to minimize smoke taint in wines following bushfires.

Techniques for Mitigating the Effects of Smoke Taint While Maintaining Quality in Wine Production: A Review

“…More recently, Fuentes et al used an e-nose instrument, in combination with artificial intelligence, as a tool for the rapid assessment of smoke contamination of grapes and wine [ 76 ]. This approach could provide winemakers with timely information that could be used to implement amelioration strategies, thereby minimizing smoke taint in finished wines.…”

Application of a Low-Cost Electronic Nose for Differentiation between Pathogenic Oomycetes Pythium intermedium and Phytophthora plurivora

“…In recent years there have been many proposals for the construction of low-cost electronic noses. Several groups proposed devices based on Taguchi type MQ series gas sensors [ 39 , 40 , 41 , 42 , 43 , 44 , 45 ]. Oates et al [ 46 ] presented research on a sinusoidally heated e-nose applied to olive oil type classification.…”

Integrating a Low-Cost Electronic Nose and Machine Learning Modelling to Assess Coffee Aroma Profile and Intensity

“…The latter tend to be less reliable as sensory panels are often subjected to more biases, such as the habituation error [ 15 ]. Furthermore, these techniques tend to be time-consuming, are destructive, and require larger sample sizes; they involve higher costs and high expertise for data acquisition, analysis and interpretation [ 5 , 6 , 16 , 17 , 18 , 19 , 20 ].…”

“…Electronic noses (e-noses) were first designed and proposed in the early 1980s by Persaud and Dodd [ 21 ], who developed an e-nose using semiconductor transducers and finding that this was able to discriminate a broad range of odors. Following this, some researchers have either developed or used commercial e-noses as an alternative to traditional methods to assess aromas or other chemometrics in food and beverages such as beer [ 17 , 22 , 23 , 24 ], wine [ 16 , 25 ], meat [ 26 ], juices [ 27 , 28 ], saffron [ 29 ], and tea [ 30 , 31 , 32 ], among others. Likewise, e-noses have been used in coffee to assess aromas and predict sensory descriptors using artificial neural networks (ANN) [ 33 ], to predict the geographical origin using discriminant factorial analysis [ 4 ], to discriminate between civet and non-civet coffee [ 5 , 34 ], and to predict the roasting degree using ANN [ 35 ], among others.…”