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…

Sustaining wine identity through intra-varietal diversification

With contemporary climate change, cultivated Vitis vinifera L. is at risk as climate is a critical component in defining ecologically fitted plant materiel. While winegrowers can draw on the rich diversity among grapevine varieties to limit expected impacts (Morales-Castilla et al., 2020), replacing a signature variety that has created a sense of local distinctiveness may lead to several challenges. In order to sustain wine identity in uncertain climate outcomes, the study of intra-varietal diversity is important to reflect the adaptive and evolutionary potential of current cultivated varieties. The aim of this ongoing study is to understand to what extent can intra-varietal diversity be a climate change adaptation solution. With a focus on early (Sauvignon blanc, Riesling, Grolleau, Pinot noir) to moderate late (Chenin, Petit Verdot, Cabernet franc) ripening varieties, data was collected for flowering and veraison for the various studied accessions (from conservatory plots) and clones. For these phenological growing stages, heat requirements were established using nearby weather stations (adapted from the GFV model, Parker et al., 2013) and model performances were verified. Climate change projections were then integrated to predict the future behaviour of the intra-varietal diversity. Study findings highlight the strong phenotypic diversity of studied varieties and the importance of diversification to enhance climate change resilience. While model performances may require improvements, this study is the first step towards quantifying heat requirements of different clones and how they can provide adaptation solutions for winegrowers to sustain local wine identity in a global changing climate. As genetic diversity is an ongoing process through point mutations and epigenetic adaptations, perspective work is to explore clonal data from a wide variety of geographic locations.

Short-term relationships between climate and grapevine trunk diseases in southern French vineyards

[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"...

Modeling the suitability of Pinot Noir in Oregon’s Willamette Valley in a changing climate

Air temperature is the key driver of grapevine phenology and a significant environmental factor impacting yield and quality for a winegrape growing region. In this study the optimal downscaled CMIP5 ensemble for computing thegrowing season average temperature (GST) viticulture climate classification index was determined to spatially compute on a decadal basis predictions of the GST climate index and the grapevine sugar ripeness (GSR) model for Pinot Noir throughout the Willamette Valley (WV) American Viticultural Area (AVA). Forecasts for average temperature and a 220 g/L target sugar concentration level were computed using daily Localized Constructed Analogs (LOCA) downscaled CMIP5 historic and Representative Concentration Pathways (RCP) future climate projections of minimum and maximum daily temperature. We explore spatiotemporal trends of the GST climate classification index and Pinot Noir specific applications of the GSR phenology model for the WV AVA. Spatiotemporal computations of the GST climate index and Pinot Noir specific applications of the GSR model enable the opportunity to explore relationships between their computed values with one intent being to provide updated GST ranges that better align with current temperature-based modeling understanding of Pinot Noir grapevine phenology and the viticultural application of LOCA CMIP5 climate projections for the WV AVA. The Pinot Noir specific applications of the GSR model or the GST index with updated bounds indicate that the percent of the WV AVA area suitable for Pinot Noir production is currently at or near its peak value in the upper 80s to lower 90s of this century.

Effect of one-year cover crop and arbuscular mycorrhiza inocululation in the microbial soil community of a vineyard

The microbial composition of the soil is an important factor to consider in viticulture, since its influence on the “terroir” and on the organoleptic properties of the wine have been demonstrated. Different agronomic techniques have the potential to modify the composition and functionality of the soil microbial community. Maintaining green covers is known to increase soil microbial diversity. The direct application of inoculum of beneficial microorganisms to the soil has also been used to increase their abundance. However, the environmental conditions of each site seem to have a determining weight in the result of these practices. In this study, we compared the effect on the microbial community of a cover crop with legumes in autumn and the inoculation of grapevines with commercial inoculum bases on Rhizophagus irregularis and Funeliformis mosseae in the previous spring. The study has been carried out in a vineyard in Binissalem, Mallorca, Spain. After applying the treatments, we will analyze the soil microbial communities using the data obtained from Illumina amplification of soil DNA from the 16S and ITS regions to analyze bacteria and fungi community, respectively. In addition, we will record the physicochemical characteristics of the soil at each sampling point. The result showed that agronomic management, in the short term, has less influence than soil characteristics on the composition of the soil microbiome. With these results, we can conclude that in a vineyard, agricultural techniques should focus on improving the characteristics of the soil to improve the biodiversity of the soil microbiota.

Teasing apart terroir: the influence of management style on native yeast communities within Oregon wineries and vineyards

Newer sequencing technologies have allowed for the addition of microbes to the story of terroir. The same environmental factors that influence the phenotypic expression of a crop also shape the composition of the microbial communities found on that crop. For fermented goods, such as wine, that microbial community ultimately influences the organoleptic properties of the final product that is delivered to customers. Recent studies have begun to study the biogeography of wine-associated microbes within different growing regions, finding that communities are distinct across landscapes. Despite this new knowledge, there are still many questions about what factors drive these differences. Our goal was to quantify differences in yeast communities due to management style between seven pairs of conventional and biodynamic vineyards (14 in total) throughout Oregon, USA. We wanted to answer the following questions: 1) are yeast communities distinct between biodynamic vineyards and conventional vineyards? 2) are these differences consistent across a large geographic region? 3) can differences in yeast communities be tied to differences in metabolite profiles of the bottled wine? To collect our data we took soil, bark, leaf, and grape samples from within each vineyard from five different vines of pinot noir. We also collected must and a 10º brix sample from each winery. Using these samples, we performed 18S amplicon sequencing to identify the yeast present. We then used metabolomics to characterize the organoleptic compounds present in the bottled wine from the blocks the year that we sampled. We are actively in the process of analysing our data from this study.