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…

The characterization of Vitis vinifera L cv. Cabernet sauvignon: the contribution of Ecklonia maxima seaweed extract

Biostimulants and biofertilizers are considered environmentally friendly and cost-effective alternatives to synthetic fertilizers, plant growth regulators and crop improvement products. Broadly, plant biostimulants are expected to improve nutrient use efficiency, tolerance to abiotic stress, quality traits and availability of nutrients in the soil or rhizosphere. Currently, seaweed extracts account for more than 33% of the total plant biostimulant market. Within this category, Ascophyllum nodosum (AN), is the most widely studied and applied in biostimulant formulations.

Trans-resveratrol concentrations in wines Cabernet Sauvignon from Chile

This study evaluated the levels of trans-resveratrol in commercial wines made from Cabernet Sauvignon grapes from different valleys of Chile stilbenes. The Cabernet Sauvignon is the most planted variety in Chile, being 38% of the total vineyard country. Chile is the fourth largest wine exporter in the world, so it is important to evaluate the Cabernet-Sauvignon wines in their concentration levels of trans-resveratrol and its relation to the benefits provided to human health in moderate consumption. Evaluation comprises commercial wines from different valleys of Chile and its relationship with climatic characteristics, soil and vineyard handling.

Chemical profiling and sensory analysis of wines from resistant hybrid grape cultivars vs conventional wines

Recently, there has been a shift toward sustainable wine production, according to EU policy (F2F and Green Deal), to reduce pesticide usage, improve workplace health and safety, and prevent the impacts of climate change. These trends have gained the interest of consumers and winemakers. The cultivation of disease resistant hybrid grape cultivars (DRHGC), known as ‘PIWI’ grapes can help with these objectives [1]. This study aimed to profile white and red wines produced from DRHGC in South Tyrol (Italy). Wines produced from DRHGCs were compared with conventional wines produced by the same wineries. The measured parameters were residual sugars, organic acids, alcohol content, pigments and other phenolics by LC-QqQ/MS, colorimetric indexes (CIELab); and volatile profiles (HS-SPME-GCxGC-ToF/MS [2]).

Alimentary film to reduce cork taint and improve wine organoleptic quality

Wine quality may be compromised by mouldy off‒flavours related to cork taint. Although different compounds are considered to be involved in this wine defect, haloanisoles (HAs), and among them the 2,4,6-trichloroanisole (TCA), are claimed as the main responsible.

Multicriteria assessment of 11 agroecological viticulture systems during six years

Context and purpose of the study. Modern conventional agriculture, including viticulture, relies greatly on the use of chemical inputs, especially synthetic pesticides.

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…

Evaluation of the efficiency of dialysis membranes in the wine dealcoholization process

The global wine production is continuously evolving to meet the new demands and preferences of consumers. in this evolving scenario, it’s important to determine which trends will be short-lived and which will remain over time. The promotion of healthier habits has encouraged consumers to try to find alternatives with low or no alcohol content. The challenge for the industry is to produce an alcohol-free wine that retains the familiar aromas and mouthfeel of traditional wine but without alcohol. Ethanol is the most abundant compound in wine, excluding water.

Unveiling the viticultural heritage of Rachaya, Lebanon: genetic, ampelographic and chemical profiling of local grape varieties

Located in the western bekaa region of lebanon, rachaya is known for its extensive history of viticulture and ideal mediterranean conditions for grapevine cultivation. Despite the area’s importance in grapevine production, there is limited knowledge about the local grape varieties grown there. In this work, we conducted a detailed analysis of five local grapevine varieties in the area, obeidy, kassoufi, foddeh, aswadi, and maryami, of which little is currently known, in comparison to a set of international varieties.

Enological evaluation of the attitude of the grapevine fumin to give varietal wines

Initiatives have been ongoing in recent years to safeguard biodiversity in the oenological sector via a process of enhancement of ancient varieties, under a pressure of a market strongly oriented towards production deriving from native vines of specific geographical zones. In that sense, Aosta Valley
(Italy) has raised the need to preserve and characterize its minority vine varieties which have the potentiality to give varietal wines. Fumin represents the 7% of the production of the region with 16 hectares of vineyards and 753 hectolitres of derived wine. Due to its large phenolic potential, strong astringency and deep colour, it has long been, and is still today, assembled or blended with other varieties as occurs, for example, for the Torrette.

Effects of ethanol removal techniques on Nero d’Avola wine

Over the past two decades, climate change has contributed to an increase in sugar content in grape must, and consequently, in the ethanol levels of wines.

MODELLING THE AGEING POTENTIAL OF SYRAH RED WINES BY ACCELERATED AGEING TESTS: INFLUENCE OF ANTIOXIDANT ASSAYS AND PHENOLIC COMPOSITION

Red wine ageing is an important step in the red wine evolution and impacts its chemical and sensory characteristics through many chemicals and physico-chemical reactions. The kinetics of these evolutions depend on the wine studied and influence the wine ageing potential. Generally, high quality red wines require a longer period of bottle ageing before consumption¹. The ageing potential is an impor-tant parameter for wine quality and is related to the capacity of a wine to undergo oxidation over time². Phenolic compounds which are ones of the main substrates for oxidation can then potentially modulate ageing potential³.