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…

LARGE SURVEY OF THE CHEMICAL COMPOSITION OF WINES RESULTING OF THE PRESSING OF RED WINE MARC. FIRST RESULTS

In the Bordeaux vineyards, press red wine represents about 15% of the volume of wines. Valuing this large volume of press wine is necessary from an economic point of view, of course, but also because of their organoleptic contribution to the blend. Nevertheless, there is a lack of recent knowledge on the composition of press wines. This work aims to establish an initial assessment of their composition (aromatic and polyphenolic) and to set up hypothesis on to the links with their sensorial identity.

Proposta per un parco produttivo agrovitivinicolo dei “colli piacentini”

Le Dipartimento di Progettazione dell ‘Architettura del Politecnico di Milano et l’Istituto di Viticoltura della Facoltà d’Agraria di Piacenza dell’Università Cattolica del Sacra Cuore, ont elaboré une proposition pour réaliser, dans l’aire de colline de la province de Piacenza, un Parco Produttivo Agrovitivinicolo.

Design of microbial consortia to improve the production of aromatic amino acid derived compounds during wine fermentation

Wine contains secondary metabolites derived from aromatic amino acids (AADC), which can determine quality, stability and bioactivity. Several yeast species, as well as some lactic acid bacteria (LAB), can contribute in the production of these aromatic compounds. Winemaking should be studied as a series of microbial interactions, that work as an interconnected network, and can determine the metabolic and analytical profiles of wine. The aim of this work was to select microorganisms (yeast and LAB) based on their potential to produce AADC compounds, such as tyrosol and hydroxytyrosol, and design a microbial consortium that could increase the production of these AADC compounds in wines.

Evaluation of field inoculation of Kocuria rhizophila and Streptomyces violaceoruber as biostimulants under water availability conditions in grapevines

Agricultural productivity must promote management systems that incorporate sustainability principles, and viticulture is no exception.

Creativini: an augmented reality card game to promote the learning of the reasoning process of a technical management route for making wine 

Nowadays, the entire viticultural and enological process is wisely thought out according to the style of wine to be produced and the local climatic conditions. Acquiring the approach of a technical management route specific for wine production remains a complex learning process for students. To enhance such learning, The Ecole d’Ingénieurs de PURPAN (PURPAN), an engineering school located in Toulouse southwest France, has recently developed Creativini, a collaborative card game in English made of 150 cards spread into 14 batches. Students in groups of 3 to 6 must design a technical production route, from plant material to bottling.

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…

WINE FERMENTATION METABOLITES PRODUCED BY TWO TORULASPORA DELBRUECKII STRAINS ISOLATED FROM OKANAGAN VALLEY, BC, CANADA VINEYARDS

Wine aroma is influenced by various factors, from agricultural practices in the vineyard to the enological choices made by winemakers throughout the vinification process. Spontaneous fermentations have a characteristically deeper complexity of aromas when compared to fermentations that have been inoculated with Saccharomyces (S.) cerevisiae because of the diversity of microflora naturally present on grape skins. Non-Saccharomyces yeast are being extensively studied for their ability to positively contribute to wine aroma and flavour. These yeasts are known to liberate more bound volatile compounds present in grape must than S. cerevisiae through the enzymatic action of β-glucosidases and β-lyases1.

Impact of type of winemaking vessel on the chemical composition and sensory attributes of Sauvignon blanc wines

In this video recording of the IVES science meeting 2024, Mariona H Gil i Cortiella (Universidad Autónoma de Chile, Santiago de Chile, Chile) speaks about the impact of type of winemaking vessel on the chemical composition and sensory attributes of Sauvignon blanc wines. This presentation is based on an original article accessible for free on IVES Technical Reviews.

Measurement of synthetic solutions imitating alcoholic fermentation by dielectric spectroscopy

Having the possibility to use a wide spectrum of elecromagnetic waves, dielectric spectroscopy is a technique commonly used for electrical characterization of dielectrics or that of materials with high energy storage capacity, just to name a few. Based on the electrical excitation of dipoles (polymer chains or molecules) or ions in relation to the characteristics of a weak external electric field, this method allows the measurement of the complex permittivity or impedance of polarizable materials, each component having a characteristic dipole moment.In recent years, the food industry has also benefited from the potential offered by this technique, whether for the evaluation of fruit quality or during the pasteurization of apple juice [1-3]. As the tests are fast and do not destroy the products, dielectric spectroscopy proved to be an experimental tool suitable for online measurements as well as long-term monitoring.

Recent observations in wine oxidation

The chemistry of wine oxidation is captured in the reactions between the oxidation products, mostly reactive electrophiles, with other wine constituents. An understanding of both components and their reactions can lead to ideas and techniques to control and mitigate or enhance these reactions to allow for the desired development of the wine. Current investigations are yielding much useful information about oxidation reactions in wine.

The pyramidal organization of AOC in France: a process of identification and valorisation of terroirs

English version: Result of their history, some famous French wine countries such as Burgundy, Bordeaux or Alsace, have a hierarchical organization of their Appellations of Controlled Origin (AOC): AOC regional, communal, Premier Cru, Grand Cru.