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…

Evaluation of methods used for the isolation and characterization of grape skin and seed, and wine tannins

Validation of the phloroglucinolysis and RP-HPLC method showed selectivity and repeatability within acceptable limits for all investigated matrices. Recovery of polymeric phenols by SPE was also acceptable.

Extreme canopy management for vineyard adaptation to climate change: is it a good idea?

Climate change constitutes an enormous challenge for humankind and for all human activities, viticulture not being an exception. Long-term strategic changes are probably needed the most, but growers also need to deal with short-term changes: summers that are getting progressively warmer, earlier harvest dates and higher pH in musts and wines. In the last 10-15 years, a relevant corpus of research is being developed worldwide in order to evaluate to which extent extreme canopy management operations, aimed at reducing leaf area and, thus, limiting the source to sink ratio, could be useful to delay ripening. Although extreme canopy management can result in relevant delays in harvest dates, longer term studies, as well as detailed analysis of their implications on carbohydrate reserves, bud fertility and future yield are desirable before these practices can be recommended.

Efficient irrigation strategies and water use reduction in the high quality production regions of Priorat and Montsant (Spain)

Priorat and Montsant Appellations of Origin are located in the south of Catalonia (North‐East Spain), under severe Mediterranean climatic conditions

Le zonage viticole en Italie. État actuel et perspectives futures

Over the past few decades, viticultural research has made numerous contributions which have made it possible to better understand the behavior of the vine as well as its response to the conditions imposed on it by the environment and agronomic practices. However, these results have only rarely been used in the practical management of vineyards because the research has been carried out using partial experimental models where reality is only represented by a few factors which are sometimes even made more complex by the introduction of elements foreign to the existing situation and difficult to apply to production (varieties, methods of cultivation, management techniques, etc.). To these reasons, one could add a low popularization of the results obtained, as well as the difficulty of implementing the scientific contributions, which does not allow the different production systems to fully express their potential. This limit of viticultural research can only be exceeded by the design of integrated projects designed directly on and for the territory. Indeed, only the integrated evaluation of a viticultural agro-system, which can be achieved through zoning, makes it possible to measure, or even attribute to each element of the system, the weight it exerts on the quality of the wine.

Integrated multiblock data analysis for improved understanding of grape maturity and vineyard site contributions to wine composition and sensory domains

Much research has sought to define the complex contribution of terroir (varieties x site x cultural practices) on wine composition. This investigation applied recent advances in chemometrics to determine relative contributions of vine growth, berry maturity and site mesoclimate to wine composition and sensory profiles of Shiraz and Cabernet Sauvignon for two vintages.