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…

Comparative studies on the dynamics of fermentation of selected wine yeasts

Alcoholic fermentation is an anaerobic biochemical process of oxidation-reduction in which carbohydrates are metabolized by the action of yeast enzymes in major products

Molecular characterization of wines nucleophilic potential by ultra-performance liquid chromatography high resolution mass spectrometry

The knowledge about the molecular fraction associated to white wines oxidative stability is still poorly understood.

FUNGAL DIVERSITY AND DYNAMICS IN CHAMPAGNE VINEYARDS: FROM VINE TO WINE

Champagne is a well-known wine region in Northern France with distinct terroirs and three main grape varieties. As for any vineyard, wine quality is highly linked to the microbiological characteristics of the raw materials. However, Champagne grape microbiota, especially its fungal component, has yet to be fully characterized. Our study focused on describing this mycobiota, from vine to small scale model wine, for the two main Champagne grape varieties, Pinot Noir and Meunier, using complementary cultural and omics approaches.

Distribution and associated symptoms of grapevine trunk pathogens in South Africa

In recent studies, several grapevine trunk pathogen complexes have been identified from grapevines in South Africa. These pathogens include Eutypa lata, Phaeomoniella chlamydospora, Phaeoacremonium sp., Botryosphaeria sp. and Phomopsis sp. Trunk diseases lead to reduced yield, and grape quality as well as a decline

Genetics of adventitious root formation in grapevines

Commercial grapevine propagation relies on the ability of dormant wood material to develop adventitious roots.

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…

Valorization of winemaking by-products through circular economy approaches

Winemaking generates significant amounts of by-products, such as grape pomace and wine lees, which are primarily used for distillation and composting.

Towards a spatial analysis of antique viticultural areas: the case study of Amos (Turkey) and some other places

Interpretation of ancient texts, such as the Amos epigraphic farming leases, questions both locations and spatial extents of the viticultural area, as well as soils, landscapes, cropping methods

White wine light-strike fault: a comparison between flint and green bottles under the typical supermarket conditions

Consumer preference favors flint-glass wine bottles over the traditional dark-colored, but it is documented that light exposure can cause white wines to produce off-aromas and change in color, and consequently da[1]mage their quality. Aim of the study was to study the white wine shelf life under the typical supermarket conditions, by recording the light and temperature exposure, the colorimetric changes, and the light-strike fault. METHODS: One pilot experiment based on two white wines and eight-time points and one kinetic experiment based on four white wines and seven-time points were designed and realized using a typical supermarket shelf for 32 and 50 days, correspondently. By installing prototype sensors at 32 points of the shelf, the temperature, UV, IR, and Visible light exposure were registered every 10 min. Approximately 600 commercial wines, bottled in flint and colored glass, were used. The colorimetric changes of the wines were registered and the light-strike fault was evaluated.

Smoke taint: Understanding and addressing the compositional consequences of grapevine exposure to smoke

Climate change has become a major challenge for grape and wine production around the world

Quelles cibles moléculaires pourraient expliquer l’effet du terroir sur la composition des baies en sucres et acides?

Le manque de connaissances concernant la physiologie de la maturation du raisin a longtemps interdit d’interpréter l’effet du terroir ou du millésime sur la qualité des vendanges en termes moléculaires. L’hypothèse selon laquelle c’est la perméabilité membranaire qui contrôlerait le sens comme l’intensité du stockage des acides est pourtant déjà ancienne (1). L’étude du transport des acides organiques et de son coût énergétique permet d’avancer certaines hypothèses concemant les sites potentiels de la régulation du contenu en sucres et acides du raisin sous l’effet de paramètres environnementaux.