Macrowine 2021
IVES 9 IVES Conference Series 9 Beyond classical statistics – data fusion coupled with pattern recognition

Beyond classical statistics – data fusion coupled with pattern recognition

Abstract

AIM: Patterns in data obtained from wine chemical and sensory evaluations are difficult to infer using classical statistics. Pattern recognition can be resolved by coupling data fusion with machine learning techniques, possibly leading to new hypotheses being formed. This study demonstrates the applicability of two pattern recognition approaches using as case study involving Chenin Blanc wines (recently bottled and after two years storage) from young (35 years) vines.

METHODS: Sensory (sorting (Mafata et al. 2020)) and chemical (NMR: nuclear magnetic resonance, HRMS: high resolution mass spectrometry, and UV-Vis: ultraviolet spectrophotometry) data were collected for the young and aged (two years in the bottle) wines. Data sets were combined using multiple factor analysis (MFA). Exploratory unsupervised cluster analysis was performed by agglomerative hierarchical clustering (AHC) and Fuzzy-k means (Bezdek 1981). Optimal cluster conditions were found for both methods and the cophenetic coefficient was used to assess the most confident clustering method.

RESULTS: Since large data sets were fused, the models were very complex. There were no consistent clustering patterns when varying clustering conditions, signalling high similarity between samples. The samples could not confidently be distinguished from one another even at the highest optimized conditions. Although Fuzzy-k means gave more confident clustering, it was still not sufficient for solving classification issues in this sample set.

CONCLUSIONS:

Fuzzy-k means was better at resolving the natural grouping of samples. Coupled to data fusion, it could potentially lead to better pattern recognition, especially for oenological chemical and sensory data. The fuzzy approach should be explored, keeping in mind it is more sensitive to small differences in the data compared to classical statistics.

DOI:

Publication date: September 7, 2021

Issue: Macrowine 2021

Type: Article

Authors

Mpho Mafata, Jeanne

1South African Grape and Wine Research Institute, Department of Viticulture and Oenology, Stellenbosch University & 2School for Data Science and Computational Thinking, Stellenbosch University, South Africa, BRAND, South African Grape and Wine Research Institute, Department of Viticulture and Oenology, Stellenbosch University, South Africa  Astrid, BUICA, South African Grape and Wine Research Institute, Department of Viticulture and Oenology, Stellenbosch University

Contact the author

Keywords

data fusion, pattern recognition, machine learning, artificial intelligence, multiple factor analysis, fuzzy-k means, cluster analysis

Citation

Related articles…

History of inorganic and isotopic signatures in Champagne over the last century: lessons

The notion of «terroir» refers to the link between the composition, quality and taste of a wine, on the one hand, and its place of origin, on the other. It involves, among other things, the signature of soil elements, as well as the influence of climatic conditions and plant material used. The composition of the wine is also influenced by the winemaking, storage and bottling processes. We were lucky enough to have a time series of the same champagne, from the end of the first world war to the present. On this exceptional time series, we followed, with the most advanced methods, all the elemental signatures by isotopic multi-dilution, the evolution of the isotopic ratios of heavy elements with very high precision of Sr, Pb, B and Cu.

Influence of processing parameters on aroma profile of conventional and ecological Cabernet-Sauvignon red wine during concentration by reverse osmosis

Wine aroma represents one of the most important quality parameter and it is influenced by various factors (viticulture and vinification techniques, climate or storage conditions etc.). Wines produced from conventionally and ecologically grown grapes of same variety have different chemical composition and aroma profile [1]. Aroma profile of wine can be also influenced by additional treatment of wine, such as concentration of wine by reverse osmosis (RO). Reverse osmosis represents a pressure-driven membrane separation technique that separates the initial wine on the retentate or concentrate that is retained on the membrane, and permeate that passes through it [2]. Wine permeate usually containes water, ethanol, acetic acid and several low molecular weight compounds that can pass through the membrane. This property enables the use of reverse osmosis membranes for wine concentration, partial dealcoholization, acetic acid or aroma correction [3,4].

Distinctive flavour or taint? The case of smoky characters in wine

Forest fires in the vicinity of vineyards have significantly increased in the last decade and are a concern for grapegrowers and winemakers in many wine producing countries. The fires cause smoke drift throughout vineyards which cannot be avoided and may result in the production of wines described as ‘smoke tainted’. Such wines are characterized by undesirable sensory characters described as ‘smoky’, ‘burnt’, ‘ash’ aromas and flavours, and also may cause a lingering, unpleasant ashy aftertaste [1; 2].

Influence of cork density upon cork stopper resiliency after opening a sparkling wine bottle

After Champagne popping, the first consumer’s observation is the shape of the cork stopper. Consumers expect a “mushroom shape”. Nevertheless, we sometimes observe a “barrel” shape due to inappropriate cork’s elastic properties. The aim of this study was to follow the loss of cork stopper resiliency during 26 months according to the density (d) of the cork in contact with the wine. 1680 disks were weighed + measured and divided in 6 density classes: High (H1 d= 0,19 g/cm3 – H2 d= 0,21 g/cm3), Medium (M, not studied) and Low (L1 d= 0,13 g/cm3 – L2 d= 0,14 g/cm3). Then, 138 technical cork stoppers were produced for each of the 4 studied groups. These corks consisted of an agglomerated natural cork granule body to which two natural cork disks were glued. A total of 552 bottles of sparkling wine were closed with these corks and open after 13, 19 and 26 months to follow cork resiliencies. Wine bottles were stored horizontally; thus, the external natural cork disks were in contact to the wine. During the 26 months of the study, highly significant differences (ANOVA) were observed between the resiliencies of H-corks and those of L-corks, whatever the time studied. The diameters of the L-corks were statistically higher than those of the H-corks. No significant differences were observed between L1 and L2 corks. At the opposite, differences were noted between H1 and H2 at 19 and 26 months. This could be explained by the heterogeneity of the resiliency that was higher for H-corks than for L-corks. Finally, the corks were visually (12 judges) divided in 3 classes corresponding to high (expected mushroom shape, i.e high resiliency), medium (irregular shape of the disk in contact with the wine and/or low premature deterioration of the expected resiliency) and low qualities (barrel shape = premature deterioration of the resiliency). The corks were also divided in 3 categories corresponding to 0-33%, 34-66% and 67-100% resiliency. A strong correlation was noted between the visual and the instrumental categorizations. This study strongly evidenced 1) the importance of the cork density on the cork stopper behaviour when opening the bottle and 2) the interest of an instrumental approach reflecting the consumer’s perception.

Measurement of grape vine growth for model evaluation

Within a research project for simulating the nitrogen turnover in vineyard soils and the nitrogen uptake by the grape vine, a previously developed plant growth model (Nendel and Kersebaum 2004) had to be evaluated. A dataset was obtained from a monitoring experiment at three vineyard sites with different soil types, conducted in the years 2003 and 2004.

Macrowine 2021
IVES 9 IVES Conference Series 9 Beyond classical statistics – data fusion coupled with pattern recognition

Beyond classical statistics – data fusion coupled with pattern recognition

Abstract

Content of the article

References

Section for all references

DOI:

Publication date: September 7, 2021

Issue: (ex: Issue: Terclim 2023)

Type: typeofpublication

Authors

author1, author2, author3

Presenting author

Description

List of affiliations ¹ ² ³

Contact the author

Email address (with mailto: link)

Keywords

List of different keywords (keyword1, keyword2, keyword3)

Tags

Citation

Related articles…

Impact of copper residues in grape must on alcoholic fermentation: effects on yeast performance, acetaldehyde and SO2 production

A relevant trend in winemaking is to reduce the use of chemical compounds in both the vineyard and winery.

Late winter pruning induces a maturity delay under temperature-increased conditions in cv. Merlot from Chile

Chile is considered vulnerable to climate change; and these phenomena affect several mechanisms in the grape physiology and quality. The global temperature increase affects sugar contents, organic acids, and phenolic compounds in grapes, producing an imbalance maturity. In this sense, an alternative to reduce the impact is to perform pruning after vine budburst, known as “Late Pruning” (LP).

Monferace a new “old style” for Grignolino wine, an autochthonous Italian variety: unity in diversity

Monferace project is born from an idea of 12 winegrowers willing to create a new “old style” Grignolino wine and inspired byancient winemaking techniques of this variety (1). Monferace wine is produced with 100% Grignolino grapes after 40 months of ageing, of which 24 in wooden barrels of different volumes. Grignolino is an autochthonous Italian variety cultivated in Piedmont (north-west Italy), recently indicated as a “nephew” of the famous Nebbiolo (2) and is used to produce three different DOC wines. The Monferace Grignolino is cultivated in the geographical area identified in the Aleramic Monferrato, defined by the Po and Tanaro rivers, in the heart of Piedmont and the produced wine is characterized by a high content of tannins, marked when young, that evolve over the years. Its color is generally slight ruby red and garnet red with orange highlights with ageing.

Vine environment interaction as a method for land viticultural evaluation. An experience in Friuli Venezia Giulia (N-E of Italy)

For a long time environment was known as one of the most important factors to characterize the quality of wines but at the same time it appears very difficult to distinguish inside the “terroir” the role of the single factor. These remarks partially explain why methods for viticultural evaluation are often quite different (Amerine et al., 1944; Antoniazzi et al., 1986; Asselin et al., 1987; Astruc et al., 1980; Bonfils, 1977; Boselli, 1991; Colugnati, 1990; Costantinescu, 1967; Costantini et al., 1987; Dutt et al., 1981; Falcetti et al., 1992; Fregoni et al., 1992; Hidalgo, 1980; Intrieri et al., 1988; Laville, 1990; Morlat et al., 1991; Scienza et al., 1990; Shubert et al., 1987; Turri et al., 1991).