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…

Rootstock regulation of scion phenotypes: the relationship between rootstock parentage and petiole mineral concentration

Grapevine is grown grafted in most of the world largely because of Phylloxera. Rootstocks not only provide tolerance to Phylloxera, but also ensure the supply of water and mineral nutrients to the scion. Rootstocks are an important means of adaptation to environmental conditions if we want to conserve the typical features of the currently used scion genotypes. To aid this adaptation, we can exploit the large diversity of rootstocks used worldwide. To fully explore this existing rootstock diversity, this work benefits from the unique GreffAdapt vineyard, in which four scion genotypes were studied onto 55 commercial rootstocks in three blocks. The aim of this study was to characterise rootstock regulation of scion mineral status and how it relates to scion development.

Influence of coinoculation of L. plantarum and O. oeni on the color and composition of Tempranillo wines

AIM: The aim of this research was to determine the influence of performing malolactic fermentation (MLF) of Tempranillo wines by coinoculation with Lactobacillus plantarum or Oenococcus oeni and Saccharomycescerevisiae on the composition and color of the final wines in comparison with sequential inoculation with Oenococcus oeni and spontaneous MLF. METHODS: Around 1500 Kg of Tempranillo grapes from Pagos de Anguix winery (Anguix, AOC Ribera de Duero, Spain) were harvested at the optimal maturity

Terroir influence on growth, grapes and grenache wines in the AOC priorat, northeast Spain

The Mediterranean climate of The Priorat AOC, situated behind the coastal mountain range of Tarragona, tends towards continentality with very little precipitation during the vegetation cycle. The soil is poor, dry and rocky, largely composed of slate schist, known as “llicorella”. Vines primarily grow on steep slopes and terraces.

Composition and molar mass distribution of different must and wine colloids

A major problem for winemakers is the formation of proteinaceous haze after bottling. Although the exact mechanisms remain unclear, this haze is formed by unfolding and agglomeration of grape proteins, being additionally influenced by numerous further factors.

The role of phytoplasma effector interaction with phosphoglucomutase in the pathogenicity of ‘Candidatus Phytoplasma solani’ in grapevine 

Bois noir is the most widespread phytoplasma grapevine disease in Europe. It is associated with ‘Candidatus Phytoplasma solani’. In symptomatic grapevines cv. ‘Zweigelt’ infected with ‘Ca. P. solani’ compared with uninfected grapevines, metabolic pathways associated with phosphorylated sugar production were induced both at the transcriptional level and at the level of activity of the corresponding enzymes (Dermastia et al., 2021, Int. J. Mol. Sci. 22: 3531). In particular, the expression of gene coding for phosphoglucoisomerase was upregulated, resulting in increased phosphoglucoisomerase enzyme activity.

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…

Qualitative and productive characterization of a minority variety: ‘Branco lexítimo’ in DO Ribeira Sacra (Spain)

The actual climate changes, together with the strong regulation of the European Union and Spanish government, in search of sustainable viticulture, have forced the recovery of minority varieties, expanding the range of grape varieties, as well as the possible development of wines with unique profiles. In the Ribeira Sacra DO (Spain), a comparative study of the agronomic and qualitative behavior of the ‘Branco lexítimo’ variety has been carried out, compared to the majority white variety in the DO: ‘Godello’, located in the same study plot, with identic soil and climatic conditions. The study contemplated the analysis of phenology and leaf water potential, as well as the productive results and the analysis of the must quality, during four seasons: 2018 – 2021.

New antibacterial peptides produced by Saccharomyces cerevisiae responsible for the inhibition of malolactic fermentation

In winemaking, several antimicrobial peptides (AMPs) produced by different strains of Saccharomyces cerevisiae were found to be responsible for the inhibition of malolactic fermentation (MLF) carried out by some strains of Oenococcus oeni. However, only two AMPs produced by one of the yeast strains studied were totally identified and their mechanism of action was described. In an attempt to identify new AMPs, a 5-10 kDa peptidic fraction produced by an oenological strain of S. cerevisiae and previously shown to strongly inhibit MLF carried out by a strain of O. oeni was further purified.

IBMP-Polypenol interactions: Impact on volatility and sensory perception in model wine solution

3-Isobutyl-2-methoxypyrazine (IBMP) is one of the key molecules in wine aroma with a bell pepper aroma and a very low threshold in wine, 1-6 ng/L for white wine and 10-16 ng/L in red wine1. The differences in these thresholds are likely due to IBMP-non volatile matrix interactions. It has indeed been shown that polyphenols may influence the volatility of flavor compounds2. In the present study, we focus on IBMP-polyphenols interactions in relation to volatility and sensory perception in model wine solution. Methods: 1. GC-MS Static Headspace Analysis: Samples were analyzed by Static headspace analysis with an Agilent 7890A gas chromatograph coupled to HP 5975C mass spectrometry detector (Agilent Technologies, Santa Clara, CA, USA).

Grapevine nitrogen dynamics as a function of crop thinning

Context and purpose. Nitrogen (N) is crucial for plant development but is used inefficiently, with only 30–40% of the fertilizer assimilated by crops, leading to significant environmental losses.

Sensory characterisation and consumer perspectives of Australian Cabernet Sauvignon wine typicity

Aim: To identify the sensory attributes responsible for the typicity of Cabernet Sauvignon wines from three Australian Geographical Indications (GIs) and to explore consumer purchase behaviour and preference with regard to regional wines.