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…

Impact of climate change on the viticultural climate of the Protected Designation of Origin “Jumilla” (SE Spain)

Protected Designation of Origin “Jumilla” (PDO Jumilla) is located in the Spanish provinces of Albacete and Murcia, in the South-eastern part of the Iberian Peninsula, where most of the models predict a severe impact of climate change in next decades. PDO Jumilla covers an area of 247,054 hectares, of which more than 22,000 hectares

Accumulation of polyphenols in Barbera and Nebbiolo leaves during the vegetative season

Grapevine berries produce thousands of secondary metabolites of diverse chemical nature that have been largely detailed in the past due to their importance for defining wine quality. The wide Vitis vinifera diversity, resulting in thousands of different varieties well detailed in many studies regarding berries, is still not investigated in vegetative organs, leaves in particular. Deepening knowledge related to this aspect could be of great interest for many reasons (for example the possibility of using leaf extract for pharmaceutical, cosmetic and nutrition purposes) but, above all, for understanding the susceptibility of different grapevine varieties to pathogens.

Trans-resveratrol concentrations in wines Cabernet Sauvignon from Chile

This study evaluated the levels of trans-resveratrol in commercial wines made from Cabernet Sauvignon grapes from different valleys of Chile stilbenes. The Cabernet Sauvignon is the most planted variety in Chile, being 38% of the total vineyard country. Chile is the fourth largest wine exporter in the world, so it is important to evaluate the Cabernet-Sauvignon wines in their concentration levels of trans-resveratrol and its relation to the benefits provided to human health in moderate consumption. Evaluation comprises commercial wines from different valleys of Chile and its relationship with climatic characteristics, soil and vineyard handling.

Effects of winemaking variables on the chemical and sensory quality of Schiava wines up to one year storage in bottle

The interactive effects of three major enological variables were evaluated on the quality of Schiava wine up to one year of storage in bottle.

How can yeast modulate Divona’s aromatic profile?

Volatile thiols play a key role in the aromatic expression of white wines, contributing to notes such as passion fruit, grapefruit, and herbal nuances [1]. These compounds, present as non-volatile precursors in grapes, require enzymatic activation to be released and realize their aromatic potential.

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…

From precursor identification to the study of the distribution of 3-methyl-2,4-nonanedione in red wines and spirits

Prematurely aged red wines are marked by intense prune and fig aromatic nuances that dominate the complex bouquet that can be achieved through bottle aging.

Molecular binding mechanisms between grape seed polypeptides and wine anthocyanins by fluorescence spectroscopy and computational techniques

In recent years, proteins endogenous to grape have become of great interest to the wine industry because they represent a new alternative to other biopolymers subjected to more legal restrictions (i.e. animal origin and synthetics) that can be used in technological applications to modulate sensory attributes such as wine color and have a positive impact on wine quality.

The “green gold” @fem: assessing grapevine germplasm diversity to crossbreed the varieties of the future

Context and purpose of the study. To date over 3,000 grapevine accessions have been collected at Fondazione Edmund Mach (FEM).

A worldwide perspective on viticultural zoning

Cet article répertorie les intérêts et problèmes du zonage viticole dans une perspective mondiale. Le zonage est un besoin pour chacun des vignobles mondiaux où il correspond à des applications, définitions et approches variées. Les objectifs du zonage changent de concert avec les besoins du marché mondial du vin, qui ne cesse de croître.

Productivity, quality, and thermal needs of the Piedirosso vine: four years of observations

The effects of temperature on cv Piedirosso, indigenous of the Campania region (South of Italy), were tested in order to study its possible influence on grapevine and to discover how to optimize the qualitative expression