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…

Digitalization and valorization of the genotypic and phenotypic information retained within the FEM grapevine germplasm

The maintenance and valorization of genetic diversity is an undoubtable resource for the viticulture of the future, since the climate crisis is forcing us to think of new, more resilient varieties. For this reason, the grapevine germplasm of the Fondazione Edmund Mach has been continuously expanded in the last decade to a total of 3,120 accessions, whose trueness-to-type has been verified by means of the universal set of nine microsatellites. About two thirds are V. vinifera subsp. vinifera accessions, while the rest consists of naturalized and selected hybrids, V. vinifera subsp. sylvestris, and pure species. The genetic material has also been characterized over three consecutive years for ampelographic, vine development, and biotic stress response traits to be exploited for experimental purposes.

Climatic zoning of viticultural production periods over the year in the tropical zone: application of the methodology of the Geoviticulture MCC system

L’objectif de cette recherche est le zonage climatique des périodes viticoles de l’année dans la Vallée du São Francisco, région brésilienne productrice de vins située en climat tropical semi-aride. Dans cette région, la production peut être échelonnée sur tous les mois de l’année.

Growing characteristics of new PIWI varieties from the breeding program in the Czech Republic

Context and purpose of the study. The breeding of PIWI varieties has a long tradition in the Czech Republic. In the last two years, 9 new PIWI varieties have been registered.

Accurate Quantification of Quality Compounds and Varietal Classification from Grape Extracts using the Absorbance-Transmittance Fluorescence Excitation Emission Matrix (A-TEEM) Method and Machine Learning

Rapid and accurate quantification of grape berry phenolics, anthocyanins and tannins, and identification of grape varieties are both important for effective quality control of harvesting and initial processing for wine making. Current reference technologies including High Performance Liquid Chromatography (HPLC) can be rate limiting and too complex and expensive for effective field operations

Unveiling the secrets of catechin: insights from NMR spectroscopy

Catechins, a class of flavonoids found in foods and beverages such as wine and tea, exhibit potent antioxidant properties that contribute to various health benefits.[1]

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…

Use of computational modelling for selecting adsorbents for improved fining of wine

The occurrence of faults and taints in wine, such as those caused by microbial spoilage or various taints, have resulted in significant financial losses to wine producers. The wine industry commits significant financial resources towards fining and taint removal processes each year. Fining involves the addition of one or more adsorptive substrates to juice or wine to bind certain components, thus reducing their concentration [1]. However, these processes are often not selective and can also remove desirable flavour and aroma compounds.

HEAT BERRY : Sensitivity of berries ripening to higher temperature and impact on phenolic compounds in wine

The grapevine is an important economical crop that is very sensitive to climate changes and microclimate. The observations made during the last decades at a vineyard scale all concur to show the impact of climate change on vine physiology, resulting in accelerated phenology and earlier harvest (Jones and Davis 2000). It is well-known that berry content is affected by the ambient temperature. While the first experiences were primarily conducted on the impact of temperature on anthocyanin accumulation in the grape, few studies have focused on others component of phenolic metabolism, such as tannins.

International Terroir Congress: 14 years of scientific proceedings!

We are a partner of the International Terroir Congress. For 4 months, our team has been putting the congress archives online. We are very proud to announce that the 14 years of archives are finally available. All archives of the International Terroir Congress are...

A comprehensive ecological study of grapevine sensitivity to temperature; how terroir will shift under climate change

Fossil fuel combustion continues to drive increases in atmospheric carbon dioxide, consequently elevating the global annual mean temperature and specifically increasing the growing season temperatures in many of the world’s most important wine growing regions (IPCC 2014; Jones et al 2005). Grapes are sensitive to changes in growing season temperatures, and past models have shown a direct link between warming temperatures and earlier harvest dates (Cook and Wolkovich 2016). Globally, there have been shifts of 1-2 weeks for wine growing regions (Wolkovich et al 2017 and references within). The phenological shifts resulting from growing season temperature increases are documented internationally, and models predicting phenology using temperature are becoming more precise (Parker et al 2011).

Functionality of different inter-stimulus rinse protocols for the sensory analysis of wildfire affected wines

From the effect of global climate change, wildfire occurrence during grape ripening has increased. These wildfires produce smoke that can carry organic compounds to a vineyard. These smoke compounds are adsorbed in the grape berry and result in wines with elevated levels of smoke-related phenols. These wines are described as having a smokey, burnt, and dirty aroma (Kristic et al, 2015). Not only are volatile phenols carried by smoke, but additionally glycoconjugate forms of these phenols are present as will. These have been found to have a large impact on the flavor of wines, being the cause of a lasting ashy aftertaste post consumption (Parker et al, 2012). When evaluating the sensory profile of these wines when tasted one after the other, there is an observed problem due to the lasting nature of these undesirable attributes and high level of carry-over from sample to sample. The aim of this work is to evaluate the extent this carryover occurs, along with the best sensory practices to mitigate its influence via different inter-stimulus rinse protocols.