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…

Energy optimization of the Charmat-Martinotti refermentation process

The european union has estimated that energy consumption for wine production is about 1,750 million kwh per year, of which 500 million kwh is attributable to italy. In recent years, Italy has emerged as the world’s leading wine producer with about 50 million hectoliters per year. About 20 percent (9.8 million hectoliters) of Italian wine is marketed after refermentation according to the Charmat-Martinotti method.

A fast and sensitive method for total tannin determination in wine based on the substoichiometric quenching of silicon-rhodamine conjugates

Tannins are chemically diverse polyphenols contributing to important sensory attributes of food and beverages. In wine, their structure and quantity depend on several factors, such as the grape variety, climate, soil, viticultural and enological practices and the wine-aging process.

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

Vertical temperature gradient in the canopy provides opportunities to adapt training system in a climate change context

Aims: The aims of this study were (1) to measure the vertical temperature gradient in the vine canopy in parcels with different vineyard floor management practices and (2) to analyze the factors influencing this gradient. The objective was to investigate whether the increase of trunk height could be an adaptation strategy to reduce air temperature in the bunch zone in a context of climate change. 

Evolution of biogenic amines content in wine during sample conservation – method optimisation for analysis of biogenicamines

The present paper reports the development of an optimized method for simultaneous analysis of
8 biogenic amines (Histamine, Methylamine, Ethylamine, Tyramine, Putrescine, Cadaverine, Phenethylamine, and Isoamylamine). It is based on a method developed by Gomez-Alonso et al. in 2007.

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…

Importance of the Terror Variability Map (TVM) in Precision viticulture (PV): choice of methodology for soil classification

The Precision Viticulture (PV) is defined “as a management system that is information and technology based, is site specific and uses one or more of the following sources of data: soils, vigour, nutrients, pests, moisture, and yield among others, for optimum profitability, sustainability, and protection of the environment” (OIV, 2018, in process). The elements mentioned in the definition are an important part of the terroir components. The terroir is a tool In Viticulture, it is the analysis and study unit, and the variability of a certain situation can be due to any difference in every element or property of each factor that constitutes it, including the management.The soil and its management are those that bring the most variability to terroir.

Effect of “Terroir” on quanti-qualitative paramethers of “vino nobile di Montepulciano”

In this last ten years period, there has been many integrated and interdisciplinary studies to determine the aptitude of different zones to viticulture (Lulli et al., 1989 ; Costantini, 1992 ; Fregoni et al., 1992). The researches needed some différent knowledges about environment characteristics (soil, climate), ecology, vineyard management, vine genetic, winemaking and sensory analysis. The interaction of all these knowledge produced the assessment about the environmental vocation (Scienza et al., 1992). By means of this metodology, the “viticultural vocation” joined the word “zoning”, that is the territory parting for its ecopedological and geographical characteristics in relation to adaptative answer of winegrape (Morlat, 1989).

DNA-Free genome editing confers disease resistance in grapevine

Grapevine (Vitis Vinifera L.), one of the most important cultivated fruit crops, is facing significant challenges due to climate change. Specifically, increasing temperatures negatively impact the physiological traits and disrupt plant phenology. Additionally, increased virulence in pathogen attacks and pests leads to significant yield loss, requiring widespread application of plant protection products. Traditional agronomic practices offer only partial mitigation, requiring the development of precise and effective intervention strategies. The economic worth of viticulture has prompted continuous efforts in grapevine genetic improvement programs, traditionally involving conventional breeding and clonal selection that, however, are complex and time-consuming approaches.

Merano Wine Festival 2020

IVES was a partner of the Merano Wine Festival (innovation section), a digital event held from 6 to 10 November 2020. During this festival participants attended scientific conferences on cutting-edge topics for the wine industry. Some of the topics covered have been selected from our journals

Expanding the biotechnological potential of M. pulcherrima/fructicola clade for wine-related applications

AIM: Strains belonging to M. pulcherrima/fructicola clade are frequently isolated from flowers, fruits and grape musts, and exhibit a broad spectrum of enzymatic activities and antimicrobial potential (Morata et al., 2019; Sipiczki, 2020; Vicente et al. 2020).