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…

FUNCTIONALIZED MESOPOROUS SILICA IS A VIABLE ALTERNATIVE TO BENTONITE FOR WINE PROTEIN STABILIZATION

The presence of grape-derived heat unstable proteins can lead to haze formation in white wines [1], an instability prevented by removing these proteins by adding bentonite, a hydrated aluminum silicate that interacts electrostatically with wine proteins leading to their flocculation. Despite effective, using bentonite has several drawbacks as the costs associated with its use, the potential negative effects on wine quality, and its environmental impact, so that alternative solutions are needed.

Effect of Botrytis cinerea and esca on phenolic composition of berries and wines

This study showed that Botrytis cinerea could degrade the phenolic compounds by its enzymatic activity. It led to a diminution of skin’s anthocyanins from 20 % to 50 % and an increase level up to 40 % of individual proanthocyanins, 30 % of the %G and 25% of the %P.

Use of computational modelling for selecting adsorbents for improved fining of wine

The occurrence of faults and taints in wine, such as those caused by microbial spoilage or various taints, have resulted in significant financial losses to wine producers. The wine industry commits significant financial resources towards fining and taint removal processes each year. Fining involves the addition of one or more adsorptive substrates to juice or wine to bind certain components, thus reducing their concentration [1]. However, these processes are often not selective and can also remove desirable flavour and aroma compounds.

Influence of planting stock and training strategy on the development and productivity of Pinot noir grapevines

For cool windy climates and/or lower vigor site situations delays in vine development during vine establishment can result in a greater number of growing seasons to achieve full yield potential. Plant material and training strategies utilized are critical factors in promoting vine development and production that is appropriate to the site conditions. The objective of this study was to evaluate nursery planting stock and training strategies for their potential to achieved advanced vine development and yield.

applicazione dei metodi isotopici e dell’analisi sensoriale negli studi sull’origine dei vini

Traceability of agro-alimentary products is very important to certify their origin. This work aimed to characterize wines obtained by the same cultivar (Nero d’Avola and Fiano) – grown in regions with different soil and climate conditions during three vintages (2003-2005) – employing isotopic analyses (NMR and IRMS) and sensory analyses.

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…

Exploring the potential of Hanseniaspora vineae for quality wines production

Traditionally, non-saccharomyces yeasts were deemed undesirable in winemaking, for this reason, it is a common practice to add sulphites to prevent their proliferation during the initial stages of vinification. However, the current research on yeast diversity has unveiled numerous non-saccharomyces strains possessing advantageous traits that enrich the sensory profile of wines. The genus hanseniaspora is often associated with wine fermentation and is also commonly found on grapes.

Impact of water stress on the phenolic composition of cv. Merlot grapes, in a typical terroir of the La Mancha region (Spain)

The study was carried out in 2006 with Merlot grapes from vines grown using the trellis system, where four treatments were compared with different levels of water stress.

Which microorganisms contribute to mousy off-flavour in our wines?

In this video recording of the IVES science meeting 2024, Mariona H Gil i Cortiella (Universidad Autónoma de Chile, Santiago de Chile, Chile) speaks about Which microorganisms contribute to mousy off-flavour in owines. This presentation is based on articles accessible for free on OENO One and IVES Technical Reviews.

Influence of irrigation on water status, productivity, yield and must composition in Tempranillo grapevine under Duero Valley zone conditions

Cette étude a pour but d’évaluer la modification de l’état hydrique (potentiel hydrique foliaire), le comportement productif (matière sèche et rendement) et la expression qualitative (poids de baie, degrée Brix, pH, acidité totale, concentration polyphénolique) de la varieté Tempranillo dans la Vallée du Douro, à l’A.O. Cigales, comme conséquence de l’application d’une irrigation modérée. Pour développer l’essai on a appliqué les suivantes

Topographic modeling with GIS at Serra Gaúcha, Brazil: elements to study viticultural terroir

Brazil is historically known at the international wine market as an importer, eventhough in the last decades there was an increase in quantity and quality of the internal production. Nowadays, about 40% of fine wines comsuption of the country are national ones. The main production region is called Serra Gaúcha, where the natural conditions are heterogeneous and viticulture is develloped in small properties, mainly done by the owners family.