GiESCO 2019 banner
IVES 9 IVES Conference Series 9 GiESCO 9 GiESCO 2019 9 Aroma and quality assessment for vertical vintages using machine learning modelling based on weather and management information

Aroma and quality assessment for vertical vintages using machine learning modelling based on weather and management information

Abstract

Context and purpose of the study ‐ Wine quality traits are usually given by parameters such as aroma profile, total acidity, alcohol content, colour and phenolic content, among others. These are highly dependent on the weather conditions during the growing season and management strategies. Therefore, it is important to develop predictive models using machine learning (ML) algorithms to assess and predict wine quality traits before the winemaking process.

Material and methods ‐ Samples in duplicates of Pinot Noir wines from vertical vintages (2008 to 2013) of the same winery located in Macedon Ranges, Victoria, Australia were used to assess different chemical analytics such as i) aromas using gas chromatography – mass spectrometry, ii) color density, iii) color hue, iv) degree of red pigmentation, v) total red pigments, vi) total phenolics, vii) pH, viii) total acidity (TA), and ix) alcohol content. Data from weather conditions from the specific vintages were obtained both from the bureau of meteorology (BoM) and the Australian Wine Availability Project (AWAP) climate databases. Such data consisted of: i) solar exposure from veraison to harvest (V‐H), ii) solar exposure from September to harvest (S‐H), iii) maximum January solar exposure, iv) degree days from S‐H, v) maximum January evaporation, vi) mean maximum temperature from veraison to harvest, vii) mean minimum temperature from V‐H, viii) water balance from S‐H, ix) solar exposure from V‐H, x) degree hour accumulation with base 25 – 30 °C, xi) degree hour accumulation with base 25 °C, xii) degree hour accumulation with base 30 °C, xiii) degree hour accumulation with base 35 °C, and xiv) total cumulative degree days accumulation with base 10 °C. All data were used to develop two machine learning (ML) regression models using Matlab® R2018b. The best models obtained were using artificial neural networks (ANN) with the Levenberg‐Marquardt algorithm with 5 neurons for Model 1 and 9 neurons for Model 2. Model 1 was developed using the 14 parameters from the weather data as inputs to predict 21 aromas found in the wines from the six different vinatges. Model 2 was developed using the same 14 parameters from weather data and the eight chemical parameters as targets and outputs.

Results ‐ Both models obtained presented very high accuracy to predict wine quality trait parameters. Model 1 had an overall correlation coefficient R = 0.99 with a high performance based on the mean squared error (MSE = 0.01), while Model 2 had an overall correlation coefficient R = 0.98 with a high performance (MSE = 0.03). These models would aid in the prediction of wine quality traits before its production, which would give anticipated information to winemakers about the product they would obtain to make early decisions on wine style variations.

DOI:

Publication date: June 22, 2020

Issue: GiESCO 2019

Type: Article

Authors

Sigfredo FUENTES, Claudia GONZALEZ VIEJO, Xiaoyi WANG, Damir D. TORRICO

School of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, VIC 3010, Australia

Contact the author

Keywords

wine quality, machine learning, weather, aromas

Tags

GiESCO 2019 | IVES Conference Series

Citation

Related articles…

Assessment of the impact of actions in the vineyard and its surrounding environment on biodiversity in Rioja Alavesa (Spain)

Traditional viticulture areas have experienced in the last decades an intensification of field practices, linked to an increased use of fertilisers and phytosanitary products, and to a more intensive mechanization and uniformization of the landscape. This change in management has sometimes led to higher rates of soil erosion andloss of soil structure, fertility decline, groundwater contamination, and to an increased pressure of pests and diseases. Additionally, intensification usually leads to a simplification of landscapes, of particular concern in prestigious wine grape regions where the economical revenue encourages the conversion of land use from natural habitats to high value wine grape production. To revert this trend, it is necessary that growers implement actions that promote biodiversity in their vineyards. The aim of this study is to assess the impact of the implementation of cover crops, vegetational corridors, dry stone walls and vineyard biodiversity hotspots estimated through the study of arthropods. The work has been carried out in four vineyards in Rioja Alavesa belonging to Ostatu winery, where these infrastructures were implemented in 2020. The presence and diversity of arthropods was studied by capturing them at different times in the season and at different distances from the infrastructure using pit-fall traps in the soil and yellow, white and blue chromatic traps at the canopy level. This is a preliminary study in which all adult insects were sorted to the taxonomic level of order and Coleoptera were classified to morphospecies. The results obtained show that there is a relationship between the basic characteristics of the vineyard and the arthropods captured, with a positive effect, although also dependent on the vineyard, of the presence of infrastructure.

Impact of climate variability and change on grape yield in Italy

Viticulture is entangled with weather and climate. Therefore, areas currently suitable for grape production can be challenged by climate change. Winegrowers in Italy already experiences the effect of climate change, especially in the form of warmer growing season, more frequent drought periods, and increased frequency of weather extremes.
The aim of this study is to investigate the impact of climate variability and change on grape yield in Italy to provide winegrowers the information needed to make their business more sustainable and resilient to climate change. We computed a specific range of bioclimatic indices, selected by the International Organisation of Vine and Wine (OIV), and correlated them to grape yield data. We have worked in collaboration with some wine consortiums in northern and central Italy, which provided grape yield data for our analysis.
Using climate variables from the E-OBS dataset we investigate how the bioclimatic indices changed in the past, and the impact of this change on grape productivity in the study areas. The climate impact on productivity is also investigated by using high-resolution convection-permitting models (CPMs – 2.2 horizontal resolution), with the purpose of estimating productivity in future emission scenarios. The CPMs are likely the best available option for this kind of impact studies since they allow a better representation of small-scale processes and features, explicitly resolve deep convection, and show an improved representation of extremes. In our study, we also compare CPMs with regional climate models (RCMs – 12 km horizontal resolution) to assess the added value of high-resolution models for impact studies. Further development of our study will lead to assessing the future suitability for vine cultivation and could lead to the construction of a statistical model for future projection of grape yield.

Evolution of the amino acids content through grape ripening: Effect of foliar application of methyl jasmonate with or without urea

The parameters that determine the grape quality, and therefore the optimal harvest time, suffer variations during berry ripening, related to climate change, with the widely known problem of the gap between technological and phenolic maturities. However, there are few studies about its incidence on grape nitrogen composition. For this reason, the use of an elicitor, methyl jasmonate (MeJ), alone or with urea, is proposed as a tool to reduce climatic decoupling, allowing to establish the harvest time in order to achieve the optimum grape quality. The aim was to study the effect of MeJ and MeJ+Urea foliar applications on the evolution of Tempranillo amino acids content throughout the grape maturation. Three treatments were foliarly applied, at veraison and 7 days later: control (water), MeJ (10 mM) and MeJ+Urea (10 mM+6 kg N/ha). Grape samples were taken at five stages of maturation: day before the first and second applications, 15 days after the second application (pre-harvest), harvest day, and 15 days after harvest (post-harvest). The amino acids analysis of the samples was carried out by HPLC. Results showed that the evolution of amino acids was similar regardless of the treatment; however, foliar applications influenced the nitrogen compounds content, i.e., there was no qualitative effect but quantitative one. Most of the amino acids reached their maximum concentration in pre-harvest, being higher in grapes from the treatments than in the control. In general, no differences in grape amino acids content were observed between MeJ and MeJ+Urea treatments. Foliar applications with MeJ and MeJ+Urea enhanced the grape amino acids content, without affecting their profile, helping to optimize their quality and allowing to establish a more complete grape ripening standard. Therefore, MeJ and MeJ+Urea foliar applications can be a simple agronomic practice, which has shown promising results in order to enhance the grape quality.

Combining effect of leaf removal and natural shading on grape ripening under two irrigation strategies in Manto negro (Vitis vinifera L.)

The increasingly frequent heat waves during grape ripening pose challenges for high quality wine grape production. Defoliation is a common practice that can improve the control of diseases in bunches, but also it increases the exposure to sunlight. Grapes exposed to solar radiation reach temperatures over the optimum for berry development and maturation. This makes the development of irrigation and canopy management techniques of great importance to maximize yield and grape quality. A field experiment was carried out during 2021 using Manto negro wine grapes to study the effect of applied irrigation and different light exposure levels on grape quality. Two irrigation treatments were imposed based on the frequency and amount of water doses in a four-block experimental vineyard at Bodega Ribas (Mallorca). Three light exposure treatments were randomly applied in each irrigation plot. The light treatments included exposed clusters from pea size, non-exposed clusters, and shaded clusters after softening. Leaf area index and canopy porosity was estimated every 2 weeks. Midday leaf water potential was measured weekly. Additionally, apparent electrical conductivity was measured between rows to estimate the soil water content variability. Light and temperature sensors were installed at the bunch level to quantify the differences in bunch temperature and light intensity among treatments. The effect of irrigation and cluster light exposure on berry weight, TSS, TA, malic acid, tartaric acid, K+, and pH were analysed at 5 moments along grape ripening. During different heat waves, the natural shading technique decreased the maximum bunch temperature around 10 °C respect to the exposed bunches in both irrigation strategies. The combination of defoliation and shading techniques after softening decreased TSS at harvest and affected most of the quality parameters during the last stages of ripening, showing an interesting technique to delay ripening in warm viticulture areas.

Metabolomic discrimination of grapevine water status for Chardonnay and Pinot noir

Water status impact in viticulture has been widely explored, as it strongly affects grapevine physiology and grape chemical composition. It is considered as a key component of vitivinicultural terroir. Most of the studies concerning grapevine water status have focused on either physiological traits, or berry compounds, or traits involved in wine quality. Here, the response of grapevine to water availability during the ripening period is assessed through non-targeted metabolomics analysis of grape berries by ultra-high resolution mass spectrometry. The grapevine water status has been assessed during 2 consecutive years (2019 & 2020), through carbon isotope discrimination on juices from berries collected at maturity (21.5 brix approx.) for 2 Vitis vinifera cv. Pinot noir (PN) and Chardonnay (CH). A total of 220 grape juices were collected from 5 countries worldwide (Italy; Argentina; France; Germany; Portugal). Measured δ13C (‰) varied from -28.73 to -22.6 for PN, and from -28.79 to -21.67 for CH. These results also clearly revealed higher water stress for the 2020 vintage. The same grape juices have been analysed by Fourier Transform Ion Cyclotron Resonance Mass Spectrometry (FT-ICR-MS) and Liquid Chromatography coupled to Mass Spectrometry (LC-qTOF-MS), leading to the detection of up to 4500 CHONS containing elemental compositions, and thus likely tens of thousands of individual compounds, which include fatty acids, organic acids, peptides, phenolics, also with high levels of glycosylation. Multivariate statistical analysis revealed that up to 160 elemental compositions, covering the whole range of detected masses (100 –1000 m/z), were significantly correlated to the observed gradients of water status. Examples of chemical markers, which are representative of these complex fingerprints, include various derivatives of the known abscisic acid (ABA), such as phaesic acid or abscisic acid glucose ester, which are significantly correlated with higher water stress, regardless of the variety. Cultivar-specific behaviours could also be identified from these fingerprints. Our results provide an unprecedented representation of the metabolic diversity, which is involved in the water status regulation at the grape level, and which could contribute to a better knowledge of the grapevine mitigation strategy in a climate change context.