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…

Assessing the climate change vulnerability of European winegrowing regions by combining exposure, sensitivity and adaptive capacity indicators

Winegrowing regions recognized as protected designations of origin (PDOs) are closely tied to well defined geographic locations with a specific set of pedoclimatic attributes and strictly regulated by legal specifications. However, climate change is increasingly threatening these regions by changing local conditions and altering winegrowing processes. The vulnerability to these changes is largely heterogenous across different winegrowing regions because it is determined by individual characteristics of each region, including the capacity to adapt to new climatic conditions and the sensitivity to climate change, which depend not only on natural, but also socioeconomic and legal factors. Accurate vulnerability assessments therefore need to combine information about adaptive capacity and climate change sensitivity with projected exposure to new climatic conditions. However, most existing studies focus on specific impacts neglecting important interactions between the different factors that determine climate change vulnerability. Here, we present the first comprehensive vulnerability assessment of European wine PDOs that spatially combines multiple indicators of adaptive capacity and climate change sensitivity with high-resolution climate projections. We found that the climate change vulnerability of PDO areas largely depends on the complex interactions between physical and socioeconomic factors. Homogenous topographic conditions and a narrow varietal spectrum increase climate change vulnerability, while the skills and education of farmers, together with a good economic situation, decrease their vulnerability. Assessments of climate change consequences therefore need to consider multiple variables as well as their interrelations to provide a comprehensive understanding of the expected impacts of climate change on European PDOs. Our results provide the first vulnerability assessment for European winegrowing regions at high spatiotemporal resolution that includes multiple factors related to climate exposure, sensitivity, and adaptive capacity on the level of single winegrowing regions. They will therefore help to identify hot spots of climate change vulnerability among European PDOs and efficiently direct adaptation strategies.

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.

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"...

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.

Grape berry size is a key factor in determining New Zealand Pinot noir wine composition

Making high quality but affordable Pinot noir (PN) wine is challenging in most terroirs and New Zealand’s (NZ) situation is no exception. To increase the probability of making highly typical PN wines producers choose to grow grapes in cool climates on lower fertility soils while adopting labour intensive practices. Stringent yield targets and higher input costs necessarily mean that PN wine cost is high, and profitability lower, in line-priced varietal wine ranges. To understand the reasons why higher yielding vines are perceived to produce wines of lower quality we have undertaken an extensive study of PN in NZ. Since 2018, we established a network of twelve trial sites in three NZ regions to find individual vines that produced acceptable commercial yields (above 2.5kg per vine) and wines of composition comparable to “Icon” labels. Approximately 20% of 660 grape lots (N = 135) were selected from within a narrow juice Total Soluble Solids (TSS) range and made into single vine wines under controlled conditions. Principal Component Analysis of the vine, berry, juice and wine parameters from three vintages found grape berry mass to be most effective clustering variable. As berry mass category decreased there was a systematic increase in the probability of higher berry red colour and total phenolics with a parallel increase in wine phenolics, changed aroma fraction and decreased juice amino acids. The influence of berry size on wine composition would appear stronger than the individual effects of vintage, region, vineyard or vine yield. Our observations support the hypothesis that it is possible to produce PN wines that fall within an “Icon” benchmark composition range at yields above 2.5kg per vine provided that the Leaf Area:Fruit Weight ratio is above 12cm2 per g, mean berry mass is below 1.2g and juice TSS is above 22°Brix.