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 opportunities offered by the climate change

Based on the results of experiments since 2000 at the Institut Agro Montpellier and at INRAE – Pech Rouge, and on the international experience acquired during scientific missions, a global reflection on the opportunities offered by climate change is proposed.

Function, barriers, and the environmental benefits of reuse bottle system for wine

With 0.3 to 0.7 kg CO2eq per 0.75 L wine, the glass bottle is the main contributor to the carbon footprint of a bottle of wine.

Terroir et marché : exemples de stratégie pour les vins d’une petite région (Muscadet – Anjou – Touraine)

The designations of origin of the Loire Valley wine have been recognized according to customs and notoriety established over the centuries since the Middle Ages. There are four main production basins going up the Loire, from Nantes to the Sancerrois region: Nantes, Anjou-Saumur, Touraine and the vineyards of the Centre. In each of these basins, there is a wide range of appellations of origin which has been established according to a logic which may not seem obvious to the uninformed.

Stabulation (lees stirring) in must as a method for aroma intensification: A comparison with skin contact and a classical version of Traminer and Sauvignon blanc in Austria

In the course of this study, stabilisation (lees stirring in unclarified must) with skin contact and classic white wine vinification were compared for the Sauvignon blanc and Traminer varieties in Austria. The test wines were analysed for the volatile substances esters, free monoterpenes and fruity thiols

The use of plasma activated water in barrel disinfection: impact on oak wood composition

The use of barrels is a practice that improves the quality of wines. The porous structure of wood favors the accumulation of microorganisms that can deteriorate the quality of wines so that barrel cleaning and sanitizing treatments are essential. The burning of sulphur discs has been the most common practice in winemaking because ots biocide effect. Nevertheless, its effectiveness is still insufficient and it is harmful for human health.

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…

Towards stopping pesticides: survey identification of on-farm solutions

The winegrowing sector consumes a lot of pesticides. Changes in vineyard are necessary in order to reduce or even stop using pesticides, and thus limit their harmful impacts on health and on environment. To answer these issues, the VITAE project (2021-2026) aims at designing pesticide free grapevine systems in France. For that, we take an interest in the vineyards using solutions to strongly reduce chemicals but also biopesticides. We assume that such vineyards exist and that they are implementing solutions that could inspire the design of free- pesticide system.

Influence of toasting oak wood on ellagitannin structures

Ellagitannins (ETs) have been reported to be the main phenolic compounds found in oak wood. These compounds, belonging to the hydrolysable tannin class of polyphenols, are esters of hexahydroxydiphenic acid (HHDP) and a polyol, usually glucose or quinic acid. They own their name to their capacity to be hydrolysed and liberate ellagic acid and they have an impact on astringency and bitterness sensation, which is strongly dependant on their structure. The toasting phase is particularly crucial in barrels fabrication and influences wood composition.

Geologic and geomorphologic features applied for identification of wine terroir units by digital image processing, spectroradiometric and GIS techniques in Encruzilhada do Sul, RS, Brazil

Results in the characterization of a new wine terroir unit in south Brazil are reported. Presently, several areas in Brazil are being studied, in an effort to define new wine terroirs and improve the quality of Brazilian wines.

Rapporti tra diverse tipologie di terreno e risposte produttive e qualitative delle uve Merlot e Carmenère nell’area DOC Piave

Da anni la ricerca viticola sta orientando le sue attenzioni verso lo studio della vocazionalità degli ecosistemi viticoli, perché fulcro della produttività della vite e qualità dei suoi frutti.

Towards a sustainable winery: revalorization of green CO2 for methane production

The FUELPHORIA project explores innovative pathways for sustainable energy production, with DEMO 2 focused on transforming winery-derived CO₂ into methane (CH₄) using renewable hydrogen (H₂).