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…

Oenotannins addition in wine: can be the modulation of redox potential predictable?

The purpose of this research was to study the interaction between oenotannins and wine matrix in order to design a targeted oenotannins addition for modulating the redox status of wine. It is in fact known that oenotannins can regulate the redox potential of musts and wines since they are electroactive substances (1).

IMPACT OF ACIDIFICATION AT BOTTLING BY FUMARIC ACID ON RED WINE AFTER 2 YEARS

Global warming is responsible for a lack of organic acid in grape berries, leading to wines with higher pH and lower titrable acidity. The chemical, microbiological and organoleptic equilibriums are impacted by this change of organic acid concentration. It is common practice to acidify the wine in order to prevent these imbalances that can lead to wine defects and early spoilage. Tartaric acid (TA) is most commonly used by winemaker for wine acidification purposes. Fumaric acid (FA), which is authorized by the OIV in its member states for the inhibition of malolactic fermentation, could also be used as a potential acidification candidate since it has a better acidifying power than tartaric acid.

Sensory and consumer perceptions, and consumption barriers of low and no-alcohol wines in Trentino/Alto Adige

The growing demand for non-alcoholic beverages, driven by health-conscious consumers and shifting social norms, has positioned dealcoholized wines as a promising alternative in the global beverage industry (Akhtar et al., 2025, in press; Kakroo, 2024).

Typicality of Rioja wines: identification of sensory profiles for the three subregions of DOCa Rioja

Within the DOCa Rioja three main production areas are differentiated: Rioja Alta (RA), Rioja Alavesa (RAv) and Rioja Oriental (RO). They are three diverse territories with particular characteristics that are claimed to give rise to differentiated profiles. The present work aims at evaluating the sensory diversity of young commercial red wines in these three subregions. Therefore 30 young red wines (mainly Tempranillo and vintage 2021), ten from each subregion, were sensory described following a non-verbal free sorting task and a verbal free comment task by 32 well-established Rioja winemakers.

A new AI-based system for early and accurate vineyard yield forecasting

Vineyard yield forecasting is a key issue for vintage scheduling and optimization of winemaking operations. High errors in yield forecasting can be found in the wine industry, mainly due to the high spatial variability in vineyards, strong dependency on historical yield data, insufficient use of agroclimatic data and inadequate sampling methods

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…

Chemical systems behind wine aroma perception: overview, genesis and evolution

This talk presents a revision of our knowledge and understanding of the role played by the different aroma chemicals in the positive aroma attributes of wine. A systematic approach to classifying the different aroma chemicals of wine is presented .

Ozone to improve the implantation of Lachancea thermotolerans for improving pH in warm areas in wines with low SO2 levels

Una de las biotecnologías más potentes para disminuir el pH en vinos de zonas cálidas y en variedades de pH elevado es el uso de la levadura no-saccharomyces lachancea thermotolerans. Esta especie es capaz de formar ácido láctico a partir de azúcares, reduciendo al mismo tiempo ligeramente el grado alcohólico. Por lo tanto, mejora dos de los principales problemas de los vinos de regiones afectadas por el calentamiento global. El ácido láctico es un ácido orgánico con una buena integración sensorial en el sabor del vino, y también química y biológicamente estable durante el envejecimiento del vino.

Correlations between N,S,O-heterocycle levels and age of Champagne base wines

Champagne regulation allows winegrowers to stock small amounts of still wines in order to compensate vintages’ quality shifts mainly due to climate variations. According to their technical requirements and house style some Champagne producers (commonly named “Champagne houses”) use these stored wines in the blend in order to introduce an element of complexity. These wines possess the particularity of being aged on fine lees in thermo-regulated stainless steel tanks. The Champagne house of Veuve Clicquot Ponsardin has several wines stored this way.

Characterizing graft union formation in different scion/rootstock combinations of grapevine 

In most viticultural regions, grapevines are cultivated grafted, employing either hybrid or pure species of various American Vitis spp., such as V. berlandieri, V. rupestris, and V. riparia, as grapevine rootstocks. These rootstocks play a crucial role in providing resistance to the Phylloxera insect pest. Beyond Phylloxera resistance, it is desirable for grapevine rootstocks to exhibit resistance to other soil-borne pathogens and adaptability to abiotic stress conditions. The introduction of new rootstocks holds promise for adapting agriculture to climate change without altering the characteristics of the final harvested product.

Which risk assessment of water quality in pdo vineyards in Burgundy (France)?

To meet the demand of assessment tool of water managers we adapted to the vine production the INDIGO® method to developed initially for arable farming at the field scale.