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…

A predictive model of spatial Eca variability in the vineyard to support the monitoring of plant status

[lwp_divi_breadcrumbs home_text="IVES" use_before_icon="on" before_icon="||divi||400" module_id="publication-ariane" _builder_version="4.19.4" _module_preset="default" module_text_align="center" module_font_size="16px" text_orientation="center"...

Long-term drought resilience of traditional red grapevine varieties from a semi-arid region

In recent decades, the scarcity of water resources in agriculture in certain areas has been aggravated by climate change, which has caused an increase in temperatures, changes in rainfall patterns, as well as an increase in the frequency of extreme phenomena such as droughts and heat waves. Although the vine is considered a drought-tolerant specie, it has to satisfy important water requirements to complete its cycle, which coincides with the hottest and driest months. Achieving sustainable viticulture in this scenario requires high levels of efficiency in the use of water, a scarce resource whose use is expected to be severely restricted in the near future. In this regard, the use of drought-tolerant varieties that are able to maintain grape yield and quality could be an effective strategy to face this change. During three consecutive seasons (2018-2020) the behavior in rainfed regime of 13 traditional red grapevine varieties of the Spain central region was studied. These varieties were cultivated in a collection at Centro de Investigación de la Vid y el Vino de Castilla-La Mancha (IVICAM-IRIAF) located in Tomelloso (Castilla-La Mancha, Spain). Yield components (yield, mean bunch and berry weight, pruning weight), physicochemical parameters of the musts (brix degree, total acidity, pH) and some physiological parameters related with water stress during ripening period (δ13C, δ18O) were analysed. The application of different statistical techniques to the results showed the existence of significant differences between varieties in their response to stressful conditions. A few varieties highlighted for their high ability to adapt to drought, being able to maintain high yields due to their efficiency in the use of water. In addition, it was possible quantify to what extent climate can be a determinant in the δ18O of musts under severe water stress conditions.

Climate modeling at local scale in the Waipara winegrowing region in the climate change context

In viticulture, a warming climate can have a very significant impact on grapevine development and therefore on the quality and characteristics of wines across different spatial scales, ranging from global to local. In order to adapt wine-growing to climate change, global climate models can be used to define future scenarios, but only at the scale of major wine regions. Despite the huge progress made over the last ten years in terms of the spatial resolution of climate models (now downscaled to a few square kilometres), they are not yet sufficiently precise to account for the local climate variability associated with such parameters as local topography, in spite of these parameters being decisive for vine and wine characteristics. This study describes a method to downscale future climate scenarios to vineyard scale. Networks of data loggers have been used to collect air temperature at canopy level in the Waipara winegrowing region (New Zealand) over five growing seasons. These measurements allow the creation of fine-scale geostatistical models and maps of temperature (at 100 m resolution) for the growing season. In order to model climate change at pilot site scale, these geostatistical models have been combined with regional climate change predictions for the periods 2031-2050 and 2081-2100 based on the RCP8.5 climate change scenario. The integration of local climate variability with regionalized climate change simulations allows assessment of the impacts of climate change at the vineyard scale. The improved knowledge gained using this methodology results from the increased horizontal resolution that better addresses the concerns of winegrowers. The results provide the local winegrowers with information necessary to understand current processes, as well as historical and future viticulture trends at the scale of their site, thereby facilitating decisions about future response strategies.

Impact of yeast derivatives to increase the phenolic maturity and aroma intensity of wine

Using viticultural and enological techniques to increase aromatics in white wine is a prized yet challenging technique for commercial wine producers. Equally difficult are challenges encountered in hastening phenolic maturity and thereby increasing color intensity in red wines. The ability to alter organoleptic and visual properties of wines plays a decisive role in vintages in which grapes are not able to reach full maturity, which is seen increasingly more often as a result of climate change. A new, yeast-based product on the viticultural market may give the opportunity to increase sensory properties of finished wines. Manufacturer packaging claims these yeast derivatives intensify wine aromas of white grape varieties, as well as improve phenolic ripeness of red varieties, but the effects of this application have been little researched until now. The current study applied the yeast derivative, according to the manufacture’s instructions, to the leaves of both neutral and aromatic white wine varieties, as well as on structured red wine varieties. Chemical parameters and volatile aromatics were analyzed in grape musts and finished wines, and all wines were subjected to sensory analysis by a tasting panel. Collective results of all analyses showed that the application of the yeast derivative in the vineyard showed no effect across all varieties examined, and did not intensify white wine aromatics, nor improve phenolic ripeness and color intensity in red wine.

The effects of alternative herbicide free cover cropping systems on soil health, vine performance, berry quality and vineyard biodiversity in a climate change scenario in Switzerland

There is an urgent need in viticulture to adopt alternative herbicide-free soil management strategies to mitigate climate change, increase biodiversity, reduce plant protection products and improve soil quality while minimizing detrimental effects on grapevine’s stress tolerance and fruit quality. To propose sustainable solutions, adapted to different pedoclimatic conditions in Switzerland, we developed a multidisciplinary 4-year project, started in 2020. Objectives of the project are to a) evaluate the impact of green covers (spontaneous flora, winter cover crop and permanent ground cover) on environmental and agronomic parameters and b) develop subsequently innovative strategies for different viticultural contexts of Switzerland. The project is divided into 3 phases: 1) diagnosis, 2) on-farm and 3) on-station experiments. Phase 1) consisted in an assessment of 30 commercial vineyards all over Switzerland, where growers already use different herbicide-free soil management strategies. The most promising practices identified in this exploratory phase will be replicated in commercial vineyards across Switzerland (“on-farm”) as well as in a classical randomized block design in an experimental plot (“on-station”). For phase 1), measurements consisted in evaluation of soil status (compaction, structure, roots development), soil microbial diversity (metagenomics), plant diversity and biomass, vine physiology (water stress, vigor, leaf nitrogen) and berry quality (acidity, sugar, available nitrogen). Interestingly, the permanent ground cover resulted in a higher Shannon index thus a higher biodiversity as compared to the other itineraries. The winter cover crop increased vine nitrogen and vigor while deteriorating soil quality, leaving the soil more exposed and compacted likely due to more frequent tillage. The spontaneous flora led to higher berry sugar accumulation, less nitrogen and higher malic acid concentration putatively due to a higher water retention of the flora in a particularly wet vintage. Phases 2) and 3) are required to confirm those tendencies, over the 3 next vintages and different climatic conditions.