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…

Revealing the Barossa zone sub-divisions through sensory and chemical analysis of Shiraz wine

The Barossa zone is arguably one of the most well-recognised wine producing regions in Australia and internationally; known mainly for the production of its distinct Shiraz wines. However, within the broad Barossa geographical delimitation, a variation in terroir can be perceived and is expressed as sensorial and chemical profile differences between wines. This study aimed to explore the sub-division classification across the Barossa region using chemical and sensory measurements. Shiraz grapes from 4 different vintages and different vineyards across the Barossa (2018, n = 69; 2019, n = 72; 2020, n = 79; 2021, n = 64) were harvested and made using a standardised small lot winemaking procedure. The analysis involved a sensory descriptive analysis with a highly trained panel and chemical measurement including basic chemistry (e.g. pH, TA, alcohol content, total SO2), phenolic composition, volatile compounds, metals, proline, and polysaccharides. The datasets were combined and analysed through an unsupervised, clustering analysis. Firstly, each vintage was considered separately to investigate any vintage to vintage variation. The datasets were then combined and analysed as a whole. The number of sub-divisions based on the measurements were identified and characterised with their sensory and chemical profile and some consistencies were seen between the vintages. Preliminary analysis of the sensory results showed that in most vintages, two major groups could be identified characterised with one group showing a fruit-forward profile and another displaying savoury and cooked vegetables characters. The exploration of distinct profiles arising from the Barossa wine producing region will provide producers with valuable information about the regional potential of their wine assisting with tools to increase their target market and reputation. This study will also provide a robust and comprehensive basis to determine the distinctive terroir characteristics which exist within the Barossa wine producing region.

The modification of cultural practices in grapevine cv. Syrah, does it modify the characteristics of the musts?

The work shows the results of a year of experimentation (2020) in a Syrah variety vineyard in La Roda (Castilla-La Mancha, Spain). The trial approach was on a randomized block design with two factors: Irrigation (I) and Pruning (P).
Irrigation schedules were adjusted to apply amounts close to 1,500 m3/ha. With this provision, 2 different irrigation treatments were proposed: I1) Start of irrigation from pea-sized grape to post-harvest (providing at least 20 % of the total amount of irrigation water to be provided post-harvest); I2) Start of irrigation from pea-sized grape to harvest (usual irrigation practice in the study area). Pruning was proposed with two treatments, one at the end of January (P1), which is pruning on a conventional date; and P2) pruning carried out at the beginning of budding. In total, 4 repetitions were designed with 4 elementary plots, each one of them representing one of the proposed treatments (I1P1; I1P2; I2P1; I2P2). In total, 16 plots were worked on and each elementary plot consisted of 30 strains, distributed in 3 lines.
The productive response was evaluated with the yield results of the harvest harvested at 23 ºBrix. The qualitative response was measured in the musts through the indices of technological (acidity, pH and potassium) and phenolic maturity and aromatic compounds in free and glycosylated fractions. The treatments tested had, in general, an effect on the different variables analyzed.

The combined effects of climate, soils, and deficit irrigation on yield and quality of Touriga Nacional under high atmospheric demand in the Douro Region

Global warming is one of the biggest environmental, social and economic threats in several viticultural regions. In the Douro Valley, changes are expected in the coming years, namely an increase in temperature and a decrease in precipitation. These changes are likely to have consequences for the production and quality of wine.
The aim of this study was to explore the effects of different soil characteristics combined with several deficit irrigation strategies, managed throughout ETc references and predawn leaf water potentials thresholds, on physiology, yield, and qualitative attributes on the Touriga Nacional variety under years of mild to severe water and heat stress.
The studies were conducted over seven years (2015 to 2021) in two plots of a commercial vineyard located at Quinta do Ataíde (Symington Family Estates) planted in 2011 and 2014 at 170 meters elevation, growing under three water regimes: non-irrigated (NI) and two deficit irrigation strategies (30% and 60% ETc) assessed weekly by Ψpd. The site has an annual rainfall below 500 mm, with high atmospheric demand. Climate data was collected from a weather station, located on site. Berry ripening was followed weekly for fruit analysis. At harvest, yield, vigour and pruning weight per vine were determined from 90 vines by treatment. Each season at veraison the NDVI Index was accessed by a drone. The soils physic-chemistry in the experimental blocs were analysed and grouped by SWHC. Delta C-13 analyses were also performed per treatment in two years.Irrigation had a positive effect on yield per vine, mostly due to an increase in berry and cluster weight, and fertility index through the years. A significant increase in sugar content, colour and phenols was observed with deficit irrigation in some years, but vine vigour related to soil characteristics had by far the greatest impact on quality.

Effects of graft quality on growth and grapevine-water relations

Climate change is challenging viticulture worldwide compromising its sustainability due to warmer temperatures and the increased frequency of extreme events. Grafting Vitis vinifera L.

Phenolic composition of Tempranillo Blanco grapes changes after foliar application of urea

Our research aimed to determine the effect and efficiency of foliar application of urea on the phenolic composition of Tempranillo Blanco grapes. The field experiment was carried out in 2019 and 2020 seasons and the plot was located in D.O.Ca Rioja (North of Spain). The vineyard was Vitis vinifera L. Tempranillo Blanco and grafted on Richter-110 rootstock. The treatments were control (C), whose plants were sprayed with water and three doses of urea: plants were sprayed with urea 3 kg N/ha (U3), 6 kg N/ha (U6) and 9 kg N/ha (U9). The applications were performed in two phenological stages, pre-veraison (Pre) and veraison (Ver). Also, each of the treatments was repeated one week later. Control and treatments were performed in triplicate and arranged in a randomised block design. Grapes were harvested at optimum ripening stage. High-performance liquid chromatography was used to analyse the phenolic composition of the grapes. Finally, the results obtained from the analytical determinations – flavonols, flavanols and non-flavonoid (hydroxybenzoic acids, hydroxycinnamic acids and stilbenes) – were studied statistically by analysis of variance. The results showed that, in 2019, U6-Pre and U9-Pre treatments increased the hydroxybenzoic acid content in grapes, and also all foliar treatments applied at Pre enhanced the stilbene concentration. Moreover, U3-Ver was the only treatment that rose flavonol and stilbene contents in the Tempranillo Blanco grapes. In 2020, all treatments applied at Pre enhanced the flavonol concentration in grapes. Furthermore, U3-Pre and U9-Pre treatments increased stilbene content in grapes. Nevertheless, the hydroxybenzoic acid content was improved by U6-Ver and U9-Ver and besides, hydroxycinnamic acid concentration in grapes was increased by all treatments applied at Ver. In conclusion, the lower and highest dose of urea (U3 and U9), applied at pre-veraison, were the best treatments to improve the Tempranillo Blanco grape phenolic composition.