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…

Organic recycled mulches in sustainable viticulture: assessment of spontaneous plants communities and weed coverage

In recent years, developing more efficient and sustainable viticulture management has been essential due to the impact of climate change in semiarid regions. For this reason, the use of recycled organic mulching (ROM) in the vineyard has become an interesting strategy to cope with water stress, isolated soil from extreme temperatures and improving soil humidity, control the presence of weeds and therefore reduce the inputs of herbicides and improve soil fertility. This work aimed to analyse the effect of three different organic mulches [straw (S), grape pruning debris (GPD) and spent mushroom compost (SMC)] and two traditional soil management techniques [herbicide (H) and interrow (IN)] on weed coverage and the spontaneous plant communities’ presence. Data sampling was collected throughout the vine vegetative cycle of 2021 in La Rioja, Spain. The different soil management techniques had a clear effect on weed coverage and his development during the vine vegetative cycle. SMC and H were the treatments with the highest and the lowest coverage percentage, respectively. IN had a delayed weed emergence at the beginning of the vine vegetative cycle, but finally it reached maximum values nearby SMC. GPD and S had similar effects on weed emergence, reaching 25-30% of the maximum coverage values. A total of 29 herbaceous species were identified during the vegetative cycle, some of them very isolated and occasional. Principal component analysis (PCAs) showed a good association between spontaneous species and treatments, furthermore, specific species-treatment associations were found. Moreover, three clear groups of herbaceous communities were identified by cluster analysis. This study provides interesting information about the effect of different alternative soil management on herbaceous plant coverage and weed species communities which could contribute to making more sustainable viticulture.

A spatial explicit inventory of EU wine protected designation of origin to support decision making in a changing climate

Winemaking areas recognized as protected designations of origin (PDOs) shape important economic, environmental and cultural values that are tied to closely defined geographic locations. To preserve wine products and wine-growing practices adopted in different PDOs these areas are strictly regulated by legal specifications. However, quality viticulture is increasingly under pressure from climate change, which is altering the local conditions of many winegrowing areas. Therefore, maintaining traditional wine products will require the adoption of tailored adaptation strategies, including possible changes in the legal regulation of protected wines. To this end, it is necessary to have a comprehensive knowledge on PDOs including their extension, products and allowed practices. While there have been efforts to build databases that summarize the characteristics for individual wine PDO areas and to quantify the related effects of climate change, much information is still included only in the official documentation of the EU geographical indication register and has never been collected in a comprehensive manner. With this study we aim at filling this gap by building a spatial inventory of European wine PDOs that supports decision making in viticulture in the context of climate change. To map and characterize European wine PDOs, we analysed their legal documents and extracted relevant information useful for climate change adaptation. The output consists of a comprehensive geographical dataset that identifies the boundaries of all 1200 European wine PDOs at unprecedented spatial resolution and includes a set of legally binding regulations, such as authorized vine varieties, maximum yields and planting density. The inventory will allow researchers to analyse the impacts of climate change on European wine PDOs and support decision makers in developing tailored adaptation strategies. This includes, among others, the evaluation of new vineyard site selection, the expansion of cultivated varieties or the authorization of irrigation in vineyards.

Impact on leaf morphology of Vitis vinifera L. cvs Riesling and Cabernet Sauvignon under Free Air Carbon dioxide Enrichment (FACE)

Atmospheric carbon dioxide (CO2) concentration has continuously increased since pre-industrial times from 280 ppm in 1750, and is predicted to exceed 700 ppm by the end of 21st century. For most of C3 plant species elevated CO2 (eCO2) improve photosynthetic apparatus results in an increased plant biomass production. To investigate the effects of eCO2 on morphological leaf characteristics the two Vitis vinifera L. cultivars, Riesling and Cabernet Sauvignon, grown in the Geisenheim VineyardFACE (Free Air Carbon dioxide Enrichment) system were used. The FACE site is located at Geisenheim University (49° 59′ N, 7° 57′ E, 94 m above sea level), Germany and was implemented in 2014 comparing future atmospheric CO2-concentrations (eCO2, predicted for the mid-21st century) with current ambient CO2-conditions (aCO2). Experiments were conducted under rain-fed conditions for two consecutive years (2015 and 2016). Six leaves per repetition of the CO2 treatment were sampled in the field and immediately fixed in a FAA solution (ethanol, H2O, formaldehyde and glacial acetic acid). After 24 h leaf samples were transferred and stored in an ethanol solution. Subsequently, leaf tissue was dehydrated using ethanol series and embedded in paraffin. By using a rotary microtomesections of 5 µm were prepared and fixed on microscopic slides. Subsequent the samples were stained using consecutive staining and washing solutions. Afterwards pictures of the leaf cross-sections were taken using a light microscope and consecutive measurements were conducted with an open source image software. Differences found in leaf cross-sections of the two CO2 treatments were detected for the palisade parenchyma. Leaf thickness, upper and lower epidermis and spongy parenchyma remained less affected under eCO2 conditions. The observed results within grapevine leaf tissues can provide first insights to seasonal adaptation strategies of grapevines under future elevated CO2 concentrations.

Making sense of available information for climate change adaptation and building resilience into wine production systems across the world

Effects of climate change on viticulture systems and winemaking processes are being felt across the world. The IPCC 6thAssessment Report concluded widespread and rapid changes have occurred, the scale of recent changes being unprecedented over many centuries to many thousands of years. These changes will continue under all emission scenarios considered, including increases in frequency and intensity of hot extremes, heatwaves, heavy precipitation and droughts. Wine companies need tools and models allowing to peer into the future and identify the moment for intervention and measures for mitigation and/or avoidance. Previously, we presented conceptual guidelines for a 5-stage framework for defining adaptation strategies for wine businesses. That framework allows for direct comparison of different solutions to mitigate perceived climate change risks. Recent global climatic evolution and multiple reports of severe events since then (smoke taint, heatwave and droughts, frost, hail and floods, rising sea levels) imply urgency in providing effective tools to tackle the multiple perceived risks. A coordinated drive towards a higher level of resilience is therefore required. Recent publications such as the Australian Wine Future Climate Atlas and results from projects such as H2020 MED-GOLD inform on expected climate change impacts to the wine sector, foreseeing the climate to expect at regional and vineyard scale in coming decades. We present examples of practical application of the Climate Change Adaptation Framework (CCAF) to impacts affecting wine production in two wine regions: Barossa (Australia) and Douro (Portugal). We demonstrate feasibility of the framework for climate adaptation from available data and tools to estimate historical climate-induced profitability loss, to project it in the future and to identify critical moments when disruptions may occur if timely measures are not implemented. Finally, we discuss adaptation measures and respective timeframes for successful mitigation of disruptive risk while enhancing resilience of wine systems.

Grapevine yield estimation in a context of climate change: the GraY model

Grapevine yield is a key indicator to assess the impacts of climate change and the relevance of adaptation strategies in a vineyard landscape. At this scale, a yield model should use a number of parameters and input data in relation to the information available and be able to reproduce vineyard management decisions (e.g. soil and canopy management, irrigation). In this study, we used data from six experimental sites in Southern France (cv. Syrah) to calibrate a model of grapevine yield limited by water constraint (GraY). Each yield component (bud fertility, number of berries per bunch, berry weight) was calculated as a function of the soil water availability simulated by the WaLIS water balance model at critical phenological phases. The model was then evaluated in 10 grapegrowers’ plots, covering a diversity of biophysical and technical contexts (soil type, canopy size, irrigation, cover crop). We identified three critical periods for yield formation: after flowering on the previous year for the number of bunches and berries, around pre-veraison and post-veraison of the same year for mean berry weight. Yields were simulated with a model efficiency (EF) of 0.62 (NRMSE = 0.28). Bud fertility and number of berries per bunch were more accurately simulated (EF = 0.90 and 0.77, NRMSE = 0.06 and 0.10, respectively) than berry weight (EF = -0.31, NRMSE = 0.17). Model efficiency on the on-farm plots reached 0.71 (NRMSE = 0.37) simulating yields from 1 to 8 kg/plant. The GraY model is an original model estimating grapevine yield evolution on the basis of water availability under future climatic conditions.  It allows to evaluate the effects of various adaptation levers such as planting density, cover crop management, fruit/leaf ratio, shading and irrigation, in various production contexts.