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…

α-Terpinyl ethyl ether: stereoselective GC × GC confirmation and identification of its precursors in wine

Wines exhibit profound chemical complexity which arise from a diverse array of compounds that contribute to its sensory profile.

Lactiplantibacillus plantarum – A versatile tool for biological deacidification

Malolactic fermentation (MLF) is a secondary wine fermentation conducted by lactic acid bacteria (LAB). This fermentation is important in winemaking as it deacidifies the wine, converting L-malic acid into L-lactic acid and carbon dioxide, and it contributes to microbial stability. Wine pH is highly selective, and at pH below 3.5 generally only strains of O. oeni can survive and express malolactic activity, while under more favorable growth conditions above pH 3.5, species of Lactobacillus and Pediococcus may conduct the MLF. Among the LAB species Lactiplantibacillus plantarum strains have shown most interesting results under hot climate conditions, not only for their capacity to induce MLF, but also for their homo-fermentative properties towards hexose sugars, which makes them suitable for induction of MLF in high pH and high alcohol wines, when inoculated at the beginning of alcoholic fermentation.

South Africa’s top 10 Sauvignon blanc wines. How do the chemical and sensory profiles compare?

FNB Top 10 Sauvignon Blanc competition, presented by the Sauvignon Blanc Interest Group of South Africa and sponsored by First National Bank, is the country’s foremost platform for producers of this cultivar to showcase and benchmark their wines. Wines entered in the competition originated from all over the winegrowing regions of the country and the winning wines showed good representation of quality South African Sauvignon blanc wines. The ten selected wines were subjected to various chemical analyses including volatile thiol and methoxypyrazine determination, while the sensory profile of each wine was determined using projective mapping.

Vegetative dose heights ‘Cabernet Sauvignon’ and its influence on fruit and wine quality

The leaf area is of fundamental importance so that the plant can realize adequate levels of photosynthesis for the accumulation of reserves and to reach a suitable maturation of
the berries. In this sense, the objective was to evaluate the effect of different lengths of the stalks from the first support wire, in the must and in the wine of ‘Cabernet Sauvignon’.

Influence of polysaccharide extracts from wine by-products on the volatile composition of sparkling white wines

In the production of sparkling wines, during the second fermentation, mannoproteins are released by yeast autolysis, which affect the quality of the wines. The effect of mannoproteins has been extensively studied, and may affect aroma and foam quality. However, there are no studies on the effect of other polysaccharides such as those from grapes. Considering the large production of waste from the wine industry, it was proposed to obtain polysaccharide-rich extracts from some of these by-products[1].

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…

Teinturier grapes: Valorization as a source of high-value compounds for the Chilean food industry

The agri-food industry is constantly searching for ingredients of high functional value, healthy and of natural origin. One species of particular interest is Vitis vinifera, due to its recognized antioxidant potential. Among the grape varieties, one group possesses these antioxidant compounds not only in the skin, but also in its pulp: Teinturier. The red grape has traditionally been used for color correction purposes in winemaking, however, its high antioxidant content transforms it into a raw material of high potential for new formulations of ingredients and foods for the health and wellness market.

Interaction among grapevine cultivars (Sangiovese, Cabernet-Sauvignon and Merlot) and site of cultivation in Bolgheri (Tuscany)

Different “landscape unit” have been identified in Bolgheri area (a viticultural appellation in the Tirrenian coast of Tuscany) by the aid of pedological, landscape and agronomic observations in the 1992-1993 period. In all cultivar (Sangiovese, Cabernet Sauvignon and Merlot) x landscape unit combinations, experimental plots were chosen in homogeneous vineyards, single cordon trained (about 3300-4500 vines/hectare). Grape maturation was studied by weekly samples of berries from veraison to vintage in the 1992-1995 period. At harvest yield and must composition traits were measured and, from the most représentative plots, sixty kilograms of grapes were harvested each year and vinified according to a standardised scheme. Wines were evaluated by standard chemical and sensory analyses.

Observatoire du Grenache en Vallée du Rhône: incidence du terroir sur la diversité analytique et sensorielle des vins

Rhone Valley A.O.C. Vineyards cover more than 70 000 hectares, of wich more than 40 000 plantedwith Grenache N. The Grenache observatory was created in 1995.

Terroir zoning in appellation campo de borja (northeast Spain): Preliminary results

The components and methodology for characterization of the terroir have been described by Gómez-Miguel & Sotés (1993-2014, 2003) and Gómez-Miguel (2011) taking into account the full range of environmental factors (i.e: climate, lithology, vegetation, topography, soils, altitude, etc.), landscape variables (derived from photo-interpretation and a digital elevation model), and specific variables to the country’s viticulture (i.e: size and distribution of the vineyards, varieties, phenology, productivity, quality, designation regulations, etc.).

Infrared spectroscopy investigation of fresh grapevine organs for clustering and classification.

The spectral information acquired from fresh whole grapevine organs have yet to be fully explored. Infrared spectroscopy provides the means to rapidly measure fresh plant material and providing extensive information on the physical and chemical structure of samples.