GiESCO 2019 banner
IVES 9 IVES Conference Series 9 GiESCO 9 Machines and fire: developing a rapid detection system for grapevine smoke contamination using NIR spectroscopy and machine learning modelling

Machines and fire: developing a rapid detection system for grapevine smoke contamination using NIR spectroscopy and machine learning modelling

Abstract

Context and purpose of the study – Bushfires are a common occurrence throughout Australia and their incidence is predicted to both rise and increase in severity due to climate change. Many of these bushfires occur in areas close to wine regions, which receive different levels of exposure to smoke. Wine produced from smoke-affected grapes are characterised by unpalatable smoky aromas such as “burning rubber”, “smoked meats” and “burnt wood”. These smoke tainted wines are unprofitable and result in significant financial losses for winegrowers. This study investigated the use of near-infrared (NIR) spectroscopy and machine learning (ML) modelling for the rapid and non-destructive detection of grapevine smoke exposure by analysing grapevine leaves and/or grape berries.

Materials and methods – The trial was conducted during the 2018/2019 season at the University of Adelaide’s Waite campus in Adelaide, South Australia (34° 58’ S, 138° 38’ E) and involved the application of five different smoke and water misting treatments to Cabernet Sauvignon grapevines at approximately seven days post-veraison. Treatment vines were exposed to straw-based smoke for one hour under experimental conditions described previously by Kennison et al. (2008) and Ristic et al. (2011). Near-infrared (NIR) measurements were then taken from berries and leaves a day after smoking using the microPHAZIR TM RX NIR Analyser (Thermo Fisher Scientific, Waltham, USA) which has a spectral range of 1600-2396 nm. The NIR spectra were then used as inputs to train different ML algorithms, which resulted in two artificial neural networks (ANNs) with the best classification performance for either berry or leaf readings according to the different smoke treatments.

Results – Both ANN models found were able to correctly classify the leaf and berry spectral readings with high accuracy. The leaf model had an overall accuracy of 95.2%, 97.7% accuracy during training with a mean square error (MSE) 0.0082, 90.9% during validation with a MSE of 0.0353 and 88.1% during the testing stage with a MSE of 0.0386, while the berry model had an overall accuracy of 91.7%, 95.2% accuracy during training with a MSE of 0.0173, 86.4% during validation with a MSE of 0.0560 and 80.2% during the testing stage with a MSE of 0.0560. These results showed the potential of developing a rapid, non-destructive, in-field detection system for assessing grapevine smoke contamination following a bushfire using NIR spectroscopy and artificial neural network modelling.

DOI:

Publication date: September 28, 2023

Issue: GiESCO 2019

Type: Poster

Authors

Vasiliki SUMMERSON, Claudia GONZALEZ VIEJO, Damir TORRICO, Sigfredo FUENTES*

The University of Melbourne, School of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, Parkville 3010, Victoria, Australia

Contact the author

Keywords

bushfires, machine learning, smoke taint, climate change, non-destructive

Tags

GiESCO | GiESCO 2019 | IVES Conference Series

Citation

Related articles…

How do we describe wine imagery? Expertise shapes language usage and multimodal imagery for wine

The acquisition of wine expertise is a multi-faceted and multisensory process with implications for sensory perception, attention, memory, and language production. With the prevalence of the predictive model of brain functioning, one area of burgeoning research interest involves wine mental imagery, since the brain relies on imagined experiences to build predictions for the future. Recent evidence has shown that, for instance, those with higher imagery vividness are more susceptible to wine advertising. However, little is known about the association between mental imagery and other associated cognitive processes, such as the ability to produce words that describe such imagery. 

Toward a model of grape proanthocyanidin extraction during vinification

PAs are compartmentalised within the grape berry, and differ in their composition and degree of extractability. Within each compartment, the CWM limits PA extraction firstly by its degree of permeability and secondly its ability to complex with PA molecules.

VOLATILE COMPOUNDS AND SENSORY PROFILE OF NEBBIOLO RED WINES TREATED WITH WOOD FORMATS ALTERNATIVE TO BARRELS

In winemaking, the use of wood products alternative to barrels, has become a useful tool for the achievement of numerous oenological objectives, including the fast release of desirable volatile and polyphenolic compounds, colour stabilization, and important economic advantages if compared to the traditional barrel production. Among a huge array of variables, the wood format, the vinification protocol, especially the moment of the infusion of the woods and the exposed surface area of the alternative woods are of relevant significance, since they may influence the speed and intensity of the aroma transfer from the wood to the wine defining different sensory profiles.

Heatwaves and grapevine yield in the Douro region, crop model simulations

Heatwaves or extreme heat events can be particularly harmful to agriculture. Grapevines grown in the Douro winemaking region are particularly exposed to this threat, due to the specificities of the already warm and dry climatic conditions. Furthermore, climate change simulations point to an increase in the frequency of occurrence of these extreme heat events, therefore posing a major challenge to winegrowers in the Mediterranean type climates. The current study focuses on the application of the STICS crop model to assess the potential impacts of heatwaves in grapevine yields over the Douro valley winemaking region. For this purpose, STICS was applied to grapevines using high-resolution weather, soil and terrain datasets over the Douro. To assess the impact of heatwaves, the weather dataset (1989-2005) was artificially modified, generating periods with anomalously high temperatures (+5 ºC), at certain onset dates and with specific durations (from 5 to 9 days). The model was run with this modified weather dataset and results were compared to the original unmodified runs. The results show that heatwaves can have a very strong impact on grapevine yields, strongly depending on the onset dates and duration of the heatwaves. The highest negative impacts may result in a decrease in the yield by up to -35% in some regions. Despite some uncertainties inherent to the current modelling assessment, the present study highlights the negative impacts of heatwaves on viticultural yields in the Douro region, which is critical information for stakeholders within the winemaking sector for planning suitable adaptation measures.

Effects of fast dehydration at low temperature and relative humidity on the phenolic composition of Nebbiolo grapes

Grape postharvest dehydration is a widely used technique for the special wines production, where genetic features, ripeness degree and environmental factors strongly influence the metabolic processes [1].