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…

Natural glycolipids for the control of spoilage organisms in red wine

A natural glycolipid mixture obtained from the edible mushroom dacryopinax spathularia (“glycolipids”) is known to be an effective and approved antimicrobial treatment in non-alcoholic beverages at concentrations ranging from 5 – 100 mg/l. It has found a place alongside DMDC for the provision of microbial stability in soft drinks. These properties make the natural and sustainably produced glycolipids a promising candidate for the supplementation or replacement of SO2 in different winemaking processes.

Managing Grapevine Powdery Mildew with Ultraviolet-C Light in Washington State

Germicidal ultraviolet-C (UV-C) light has shown promising results for suppression of several plant-pathogenic microorganims, including Erysiphe necator, which attacks grapevine. In Washington State the majority of winegrape production is in a semi-arid steppe environment, with historically low powdery mildew disease pressure, making it a promising area to deploy UV-C as a disease management tool. Trials focusing on UVC application timing and frequency will assist in developing regionally-appropriate application recommendations for eastern Washington State.

INFLUENCE OF THE NITROGEN / LIPIDS RATIO OF MUSTS ON THE REVELATION OF AROMATIC COMPOUNDS IN SAUVIGNON BLANC WINE

Production of volatile compounds by yeast is known to be modulated by must nitrogen. Nevertheless, various parameter of must quality have an impact on yeast fermentation. In this study we propose to evaluate the impact of nitrogen / lipids balance on a Sauvignon Blanc grape juice (Val de Loire).
Must was prepared from the same grapes at pilot scale. Three modalities were carried out: direct pressing, direct pressing with a pre-fermentation cold stabulation and pellicular maceration before pressing.

Study of the volatile aroma profile of five Italian grape varieties submitted to controlled postharvest withering

Wines made with grapes submitted to postharvest dehydration are often referred to as “passito” or “straw wines.” This distinct style of winemaking consists of a process of water loss that allows the berries to undergo a mild water stress and senescence process [1].

Optimization of aroma production in grape cell suspensions induced by chemical elicitor

Methyl-jasmonate (MeJA) induces the production of at least 25 compounds with sesquiterpene- like mass spectra in ‘Cabernet sauvignon’. Tost effective concentration of MeJA in stimulating the production of sesquiterpenes was found to be 500 µM if added when the cell suspensions had a PCV of 35 %, and 1000 if added when the cell suspensions had a PCV of 70 %.

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…

Impacts of climate change on cv. Glera buds’ fruitfulness – 18 years of monitoring in the Conegliano-Valdobbiadene area, Italy

Context and purpose of the study. The vine is generally a very fertile plant when compared to other tree species.

The impact of global warming on Ontario’s icewine industry

Ontario’s wine regions lie at the climatic margins of commercial viticulture owing to their cold winters and short cool growing season. The gradual warming of northern latitudes projected under a human-induced climate change scenario could bring mixed benefits to these wine regions.

The role of œnology in the enhancement of terroir expression

The reality of terroir is reflected by the typicality that it confers on the wine. The relationship between the origin of wine and its quality did already exist before the appearance of œnological science. Producers and merchants have always tried to improve wine quality in order to satisfy their clients.

Do we have convergence or divergence in firms’ production and business practices in the global wine industry? 

Wine production is a globally significant and intricate industry, characterized by diverse regions, grape varieties, and producers. Competitive advantage in wine production and marketing arises from localized natural attributes known as terroir, combined with transferable expertise in agronomic practices, winemaking methods, packaging, distribution, and marketing. Wine is a very globalized product with 40% of the total output exported. Globalization has prompted discussions on convergence of business and production practices across industries, driven by technological progress and adoption of international standards. However, persisting differences in cultural norms, institutional frameworks, and regulatory environments hinder full convergence.

Architecture, microclimate, vine regulation, grape berry and wine quality: how to choose the training system according to the wine type ?

This synthetic presentation deals with :
• A description of the variability and the main models of grapevine canopy architecture in the world.
• A precision on the model « potential exposed leaf area SFEp », which estimates the potential of net carbon balance of the plant, and shows a regulating effect of high SFEp levels on production decrease.