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…

Studio dell’ambiente viticolo attraverso la parametrazione (punto di incrocio) delle curve di maturazione delle uve (pinot nero, oltrepo’ pavese pv italia settentrionale – 45° parallelo Nord)

Sono stati presi in considerazione alcuni dati agrometeorologici dell’Oltrepò Pavese (temperature e piovosità degli ultimi 80 anni) e gli studi delle curve di maturazione condotti in zona sul Pinot nero da spumante negli anni (1988-1991, 1999-2000, 2006-2008), si nota che l’aumento progressivo negli anni delle temperature attive (indice di Winkler) ha determinato un anticipo dell’invaiatura, definita dal parametro “punto di incrocio” (intersezione delle funzioni di zuccheri ed acidità nel tempo), con conseguente anticipo della data di vendemmia di circa 12-15 gg.

Aroma characterization of aged cognac spirits: contribution of volatile terpenoid compounds

Cognac spirit aromas result from the presence of a wide variety of volatile odorous compounds associated with the modalities of distilled spirit elaboration and during aging. Indeed, these odorous compounds play an essential role in the finesse and complexity of the aged Cognac.

Grape solids: new advances on the understanding of their role in enological alcoholic fermentation

Residual grape solids (suspended particles) in white and rosé musts vary depending on the clarification pro-cess. These suspended solids contain lipids (more especially phytosterols) that are essential for yeast meta-bolism and viability during fermentation in anaerobic conditions.

Colloidal stabilization of young red wine by Acacia Senegal gum: the major implication of protein-rich arabinogalactan-proteins

Acacia senegal gum (Asen) is an edible dried gummy exudate [1] added in young red wines to ensure their colloidal stability, precluding the precipitation of the coloring matter. Asen macromolecules, belonging to the arabinogalactan-protein (AGP) family [2], are hyperbranched, charged and amphiphilic heteropolysaccharides composed especially of sugars (92-96 %) and a small fraction of proteins (1-3 %). Asen is defined as a continuum of macromolecules that could be separated into three fractions by hydrophobic interaction chromatography (HIC) [3-4]. HIC-F1 (85-94 % of Asen), HIC-F2 (6-18 % of Asen) and HIC-F3 (1-3 % of Asen) are named and classified in that order according to their protein content, and then a growing hydrophobicity. The efficiency of Asen towards the coloring matter instability is evaluated according to an “efficacy test” that consists to determine the Asen quantity required to prevent the flocculation by calcium of a colloidal iron hexacyanoferrate solution (International Oenological Codex).

Barrel-to-Barrel Variation of Color and Phenolic Composition in Barrel-Aged Red Wine

Tangible variation of sensory characteristics is often perceived in wine aged in similar barrels. This variation is mostly explained by differences in the wood chemical composition, and in the production of the barrels. Despite these facts, the literature concerning barrel-to-barrel variation and its effect on wine sensory and chemical characteristics is very scarce [1]. In this study, the barrel-to-barrel variation in barrel-aged wines was examined in respect of the most important phenolic compounds of oenological interest and chromatic characteristics, considering both the effects of the (individual) barrel and cooperage. A red wine was aged in 49 new medium-toasted oak (Quercus petraea) barrels, from four cooperages, for 12 months

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…

Assessing the potential of fermentative skin contact in white winemaking on phenolic, colour, and sensory traits

Fermentative maceration in white wine production, involving extended contact with grape skins and seeds, has gained interest in recent years. The impact of this winemaking technique on wine composition and sensory properties remains underexplored.

All acids are equal, but some acids are more equal than others: (bio)acidification of wines

Insufficient acidity in grapes from warm(ing) climates is commonly corrected through addition of tartaric acid during vinification, and less so with other organic acids. One alternative approach involves bio-acidification with certain strains of Lachancea thermotolerans (LT) via lactic acid production during fermentation.

The legal concept of “cultural heritage” to refurbish the wine sector’s priorities

Following the latest oiv global report (april 26, 2024), the prevailing perception of wine consumption finds itself undergoing one of its most challenging adjustments. It’s plausible to anticipate a shift in the scope of pdo wines towards more human-centered products (wells and stiefel, 2019), necessitating the entire sector to adapt strategies to public interest patterns (touzeau, 2010: 17-31). Previously, a dominant notion of cultural property underscored the value of wine regions; the primary interest revolved around estate owners and retailers, along with vigneron tales.

The influence of vine row position in terraced Merlot vineyards on water deficit and polyphenols – case study in the Vipava Valley, Slovenia

A study was conducted in the Vipava Valley (Slovenia) to understand the effects of positioning rows of Merlot (Vitis vinifera L.) vines on terraces on plant available water, yield, and grape composition

Investigating the variability of basal crop coefficient across diverse production contexts in commercial vineyards

Vine water use is a critical determinant of vineyard management practices, especially in the context of climate change.