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…

Innovative red winemaking strategy: biosurfactant-assisted extraction and stabilization of phenolic compounds

The color is the first attribute perceived by consumers and a major factor determining the quality of red wines. This depends mainly on the content of grape anthocyanins and their extraction into the juice/wine during winemaking. Furthermore, these compounds can undergo reactions that influence the chemical and sensory characteristics of the wine. Monomeric forms are prone to oxidation and adsorption on solid parts.

Crafting wine’s signature: exploring volatile compounds from terroir to aging

The unique characteristics of terroir play a fundamental role in shaping the identity and quality of wines, influencing the aromatic complexity of young wines and their long-term aging potential. The volatile compounds responsible for these aromas are crucial to identifying and appreciating a given wine.

Applications of a novel molecular phenology scale to align the stages of grape berry development

Phenology scales widely adopted by viticulturists (i.e., BBCH or modified E-L systems) are classification tools that describe seasonal and precisely recognized stages of fruit growth and development based on specific descriptors such as visual/physical traits or easy-to-measure compositional parameters.

Monitoring the establishment of a synthetic microbial community with a potential biocontrol activity against grapevine downy mildew using a microfluidic qPCR chip

Grapevine downy mildew, caused by the oomycete Plasmopara viticola, is responsible for significant economic losses each year and for a large proportion of the fungicides used in viticulture.

Une procédure de mise à jour des zones AOC

In France, one of INAO missions is to delimit the production area of the « Appellations d’origine contrôlées » (AOC). For wine AOC, the delimitation of plots allows for identifying plots of land that respond to technical criteria of the vine location, criteria adapted in every appellation. Some old delimitations AOC are not in adequacy with their territory. Indeed, in spite the existence of a politic aiming to protect production areas AOC, urbanization, road infrastructure or quarries occupy surfaces classified in AOC today.

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…

Studying the redox state of wines under oxidative processes with a multi-parametric analysis

The detection of reducing compounds such as phenolic acids, anthocyanins or tannins is of prime importance to decipher on the antioxidant and anti-aging properties of wines.

Gamay and Gamaret winemaking processes using stems: impact on the wine chemical and organoleptic characteristics

AIM: Stalks are empirically known to bring many benefits to the wine such as alcoholic reduction, color protection or improvement of the tannic intensity. Not much used on Swiss grape varieties, the aim of this study was to identify the relevance of using this type of winemaking in the case of Gamay and Gamaret red grape varieties.

Preliminary evaluation of agronomic and enological properties of preselected grapevine clones of ‘Tempranillo’ and ‘Graciano’ in DOCa Rioja (Spain)

Cultivation of a few number of clones is causing the loss of vineyard biodiversity, resulting in the disappearance of biotypes that could be of interest to face future challenges,

Manipulating grapevine bud fruitfulness

Bud fruitfulness is a key component of reproductive performance of grapevine. It plays a significant role in annual yield variation of vineyards as it is a prerequisite of crop production in the following season. Various exogenous and endogenous factors influencing the development of inflorescence primordia (IP) have been studied. However, the research on molecular genetic control of bud fruitfulness, especially how it interacts with environmental factors is still lacking. This study aims to investigate the molecular mechanism of effects of temperature and light on grapevine bud fruitfulness during initiation and differentiation of IP.

La balance hydrique explique davantage la diversité intravariétale du titre alcoométrique du Merlot que l’accumulation des sucres

Dans le cadre de TerclimPro 2025, Charles Romieu a présenté un article IVES Technical Reviews. Retrouvez la présentation ci-dessous ainsi que l’article associé : https://ives-technicalreviews.eu/article/view/8506