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…

Characterization of different clone candidates of xinomavro according to their phenolic composition

Context and purpose of the study ‐ The aim of this study is the examination of wines of 9 different clones of a Greek grape variety Xinomavro, (ΧE1, X19, X22, X28, ΧE2 X30, X31, X35, X36, X37), with regards to their phenolic and anthocyanin content and chemical composition.

Antifungal and Laccase-Suppressing Activity of Phenolic Compounds and Their Oxidation Products on Grey Mold-Fungus Botrytis cinerea

Botrytis cinerea causes grey mold that results in severe problems for wine makers worldwide. Infected grapes lead to quality deterioration including formation of off-flavors or browning. The latter is caused by the enzyme laccase which is capable of oxidizing a wide range of phenolic compounds. Since the use of conventional pesticides is associated with many concerns of consumers and authorities regarding environmental and health related issues and may result in fungicide resistance, the development of green alternatives is gaining more attention.

Application of regenerative agriculture to viticulture: The REVINE project

Conventional viticulture improved the quality of production, but the economic costs can be unsustainable. Today, producers need to consider consumers’ demands for healthy, eco-friendly products. Institutions promote sustainable agriculture, with regenerative agriculture being the latest generation of methodologies focused on recovering losses and ensuring future sustainability. The revine project studies regenerative agricultural technology applied in mediterranean countries to provide precise indications for soil processing and effective vineyard treatments.

Leaf vine content in nutrients and trace elements in La Mancha (Spain) soils: influence of the rootstock

The use of rootstock of American origin has been the classic method of fighting against Phylloxera for more than 100 years. For this reason, it is interesting to establish if different rootstock modifies nutrient composition as well as trace elements content that could be important for determining the traceability of the vine products. A survey of four classic rootstocks (110-Richter, SO4, FERCAL and 1103-Paulsen) and four new ones (M1, M2, M3 and M4) provided by Agromillora Iberia. S.L.U., all of them grafted with the Tempranillo variety, has been carried out during 2019. The eight rootstocks were planted in pots of 500 cc, on three soils with very different characteristics from Castilla-La Mancha (Spain). In the month of July, the leaves were collected and dried in a forced air oven for seven days at 40ºC. Then, the samples were prepared for the analysis determination, carried out by X-Ray fluorescence spectrometry. The results obtained showed that in the case of content in mineral elements in leaf, separated by soil type, we can report the importance of few elements such as Si, Fe, Pb and, especially, Sr. The rootstock does not influence the composition of the vine leaf for the studied elements that are the most important in determining the geochemical footprint of the soil. The influence of the soil can be discriminated according to some elements such as Fe, Pb, Si and, especially, Sr.

CONSENSUS AND SENSORY DOMINANCE ARE DEPENDENT ON QUALITY CONCEPT DEFINITIONS

The definition of the term “quality” in sensory evaluation of food products does not seem to be consensual. Descriptive or liking methods are generally used to differentiate between wines (Lawless et al., 1997). Nevertheless, quality evaluation of a product such as wine can also relate to emotional aspects. As exposed by Costell (2002), product quality is defined as an integrated impression, like acceptability, pleasure, or emotional experiences during tasting. According to the ‘modality appropriateness’ hypothesis which predicts that wine tasters weigh the most suitable sensory inputs for a specific assess- ment (Freides, 1974; Welch & Warren, 1980), the nature of the quality definitions may modulate sensory influences.