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…

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.

Elucidating vineyard site contributions to key sensory molecules: Identification of correlations between elemental composition and volatile aroma profile of site-specific Pinot noir wines

The reproducibility of elemental profile in wines produced across multiple vintages has been previously reported using grapes from a single scion clone of Vitis vinifera L. cv. Pinot noir. The grapevines were grown on fourteen different vineyard sites, from Oregon to southern California in the U.S.A., which span distances from approximately hundreds of meters to 1450 km, while elevations range from near sea level to nearly 500 m. In addition, sensorial (i.e. aroma, taste, and mouthfeel) and chemical (i.e. polyphenolic and volatile) differences across the different vineyard sites have also been observed among these wines at two aging time points. While strong evidence exists to support that grapes grown in different regions can produce wines with unique chemical and sensorial profiles, even when a single clone is used, the understanding of growing site characteristics that result in this reproducible differentiation continues to emerge. One hypothesis is that the elemental profile that a vineyard site imparts to the grape berries and the resulting wine is an important contributor to this differentiation in chemistry and sensory of wines. For example, various classes of enzymes that catalyze the formation of key aroma compounds or their precursors require specific metals. In this work, we begin to report correlations between elemental and volatile aroma profiles of site-specific Pinot noir wines, made under standardized winemaking conditions, that have been previously shown to be distinguished separately by these chemical analyses.

Effects of organic mulches on the soil environment and yield of grapevine

Farming management practices aiming at conserving soil moisture have been developed in arid and semiarid-areas facing water scarcity problems. Organic mulching is an effective method to manipulate the crop-growing microclimate increasing crop yield by controlling soil temperature, and retaining soil moisture by reducing soil evaporation. In this sense, the effectiveness of different organic mulching materials (straw mulch and grapevine pruning debris) applied within the row of a vineyard was evaluated on the soil and on the vine in a Tempranillo vineyard located in La Rioja (Spain). Organic mulches were compared with a traditional bare soil management technique (based on the use of herbicides to avoid weed incidence). Mulching coverages favourably influenced the soil water retention throughout all the grapevine vegetative cycle. However, the soil-moisture variation was not the same under different mulching materials, being the straw mulch (SM) the one that retained more water in comparison with grapevine pruning debris (GPD) based-cover. The changes of soil moisture in the upper surface layer (0–10 cm) were highly dynamic, probably due to water vapour fluxes across the soil-atmospheric interface. However, both, SM and GPD reduced these fluctuations as compared with bare soils. A similar trend occurred with soil temperature. Both organic mulches altered soil temperature in comparison with bare soil by reducing soil temperature in summer and raising it in winter. Moreover, the same buffering effect for the temperature on the covered soil also remains in the deeper layers. To conclude, we could see that organic mulching had a positive impact on soil-moisture storage and soil temperature and the extent of this effect depends on the type of mulching materials. These changes led to higher rates of photosynthesis and stomatal conductivity compared to bare soils, also favouring crop growth and grape yields.

Photoselective shade films affect grapevine berry secondary metabolism and wine composition

Grapevine physiology and production are challenged by forecasted increases in temperature and water deficits. Within this scenario, photoselective overhead shade films are promising tools in warm viticulture areas to overcome climate change related factors. The aim of this study was to evaluate the vulnerability of ‘Cabernet Sauvignon’ grape berry to solar radiation overexposure and optimize shade film use for berry integrity. A randomized complete block design field study was conducted across two years (2020-2021) in Oakville, Napa Valley, CA, with four shade films (D1, D3, D4, D5) differing in the percent of radiation spectra transmitted and compared to an uncovered control (C0). Integrals for gas exchange parameters and mid-day stem water potential were unaffected by the shade films in 2020 and 2021. By harvest, berries from uncovered and shaded vines did not differ in their size or primary metabolism in either year. Despite precipitation exclusion during the dormant season in the shaded treatments, yield did not differ between them and the control in either season. In 2020, total skin anthocyanins (mg/g fresh mass) in the shaded treatments was greater than C0 during berry ripening and at harvest. Conversely, flavonol concentrations in 2020 were reduced in shaded vines compared to C0. The 2020 growing season highlighted the impact of heat degradation on flavonoids. Flavonoid concentrations in 2021 increased until harvest while flavonoid degradation was apparent from veraison to harvest in 2020 across shaded and control vines. Wine analyses highlighted the importance of light spectra to modify wine composition. Wine color intensity, tonality and anthocyanin values were enhanced in D4 whereas antioxidant properties were enhanced in C0 and D5 wines. Altogether, our results highlighted the need of new approaches in warm viticulture areas given the impact that composition of light has on berry and wine quality.

Phenological characterization of a wide range of Vitis Vinifera varieties

In order to study the impact of climate change on Bordeaux grape varieties and to assess the adaptation capacities of candidates to the grape varieties of this wine region to the new climatic conditions, an experimental block design composed of 52 grape varieties was set up in 2009 at the INRAE Bordeaux Aquitaine center. Among the many parameters studied, the three main phenological stages of the vine (budburst, flowering and veraison) have been closely monitored since 2012. Observations for each year, stage and variety were carried out on four independent replicates. Precocity indices have been calculated from the data obtained over the 2012-2021 period (Barbeau et al. 1998). This work allowed to group the phenological behaviour of the grapevine varieties, not only based on the timing of the subsequent developmental stages, but also on the overall precocity of the cycle and the total length of the cycle between budburst and veraison. Results regarding the variability observed among the different grape varieties for these phenological stages are presented as heat maps.