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…

Prevention of quercetin precipitation in red wines: a promising enzymatic solution

In this video recording of the IVES science meeting 2023, Simone Vincenzi (Department of agronomy, food, natural resources, animals and environment (DAFNAE), University of Padova, Italy) speaks about the prevention of quercetin precipitation in red wines with a promising enzymatic solution. This presentation is based on an original article accessible for free on OENO One.

The valorization of wine lees as a source of mannoproteins for food and wine applications

AIM. Wine yeast lees constitute a winemaking by-product that, unlike grape skins and seeds, are not sufficiently exploited to add value to the winemaking sector, as their treatment and disposal generally represents a cost for wineries [1].

Valpolicella chemical pattern of aroma ‘terroir’ evolution during aging

Valpolicella is an Italian region famous for the production of high quality red wines. Wines produced in its different sub-regions are believed to be aromatically different, as confirmed by recent studies in our laboratory. Aging is a very common practice in Valpolicella and it is required by the appellation regulation for periods up to four years. The aim of this study was to investigate the evolution, during aging, of volatile chemical composition of Valpolicella wines obtained from grapes harvested in different sub-regions during different vintages.

Landscape study of the Suzette rural district. A vineyard in the heart of the Dentelles de Montmirail

Le territoire de Suzette se développe sur un grand coteau viticole et boisé situé au cœur du site naturel des Dentelles de Montmirail (40km au nord d’Avignon). Ce site est à la fois l’un des pôles d’attraction touristique du département et le lieu d’une production viticole renommée (Gigondas, Vacqueyras, Beaumes de Venise, … ). Cet ensemble remarquable de terrasses viticoles et de crêtes rocheuses et boisées, forme un des paysages emblématiques du Vaucluse. La commune est actuellement soumise à une importante pression foncière due à une forte demande résidentielle. Le paysage du coteau forme et possède de ce fait un patrimoine culturel de valeur et une image de marque importante pour la production viticole locale.

Prise en compte et mutations de l’acidité volatile au XXe siècle : les évolutions règlementaires, scientifiques et qualitatives d’un composé du vin au regard de l’histoire

Les composés actifs du vin ont, jusqu’ici, peu fait l’objet d’études sur le temps long. Le développement de l’œnologie, de l’analyse des vins et, de manière concomitante, l’essor des règlementations vinicoles au XXe siècle révèlent pourtant au grand jour le poids de ces composés et leurs évolutions. Dans cette communication, nous souhaitons montrer comment l’acidité volatile des vins,

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…

Cordon height and deficit irrigation practices interact to affect yield and fruit quality of Cabernet Sauvignon and petite Sirah grown in a hot climate

Cabernet Sauvignon and Petite Sirah are the top red wine cultivars in CA, however, the hot climate in Fresno is not ideal for red Vitis Vinifera, particularly for berry color development. Mechanical pruning and irrigation were studied previously to significantly affect grapevine yield performance and berry quality. But there is lack of studies on cordon height and irrigation on mechanical pruned vineyard system.

Agronomical assessment of a vine « terroir » map: first results in the « AOC » Minervois region

Minervois is a vine region where the first detailed soil map was begun 30 years ago. In 2003, a new map was drawn plotting the soil-landscape associations. This map distinguishes 8 large soil units based on geology. The widest (called « marnes ») is the most complex : it is made of 57 sub-units, which leads to a high variability of the vine behaviour on this unit.

Effect of post-harvest ozone treatments on the skin phenolic composition and extractability of red winegrapes cv Nebbiolo and Barbera

Wine industry is looking forward for innovative, safe and eco-friendly antimicrobial products allowing the reduction of chemical treatments in the grape defense and the winemaking process that can affect negatively the quality of the product. Ozone has been tested in food industry giving good results in preventing fungi and bacteria growth on a wide spectrum of vegetables and fruits, due to its oxidant activity and ability to attack numerous cellular constituents. Ozone leaves no chemical residues on the food surface, decomposing itself rapidly in oxygen. Gaseous ozone has been already tested for table grapes storage and on wine grapes during withering.

Mgaloblishvili Rpv29 and Rpv31 loci reveal new insights on downy mildew resistance sources in Vitis vinifera

Downy mildew, a disease caused by Plasmopara viticola (Berk. et Curt.) Berl. and De Toni, is one of the strongest threats to grapevine (Vitis vinifera L.) production. Recently, sources of resistance to downy mildew were identified among Caucasian germplasm. Among them, the Georgian variety Mgaloblishvili revealed a unique resistance mechanism. A genome wide association study (GWAS) allowed the identification of the genetic bases of Mgaloblishvili resistance, the loci Rpv29, Rpv30 and Rpv31. To dissect the three resistance loci, Mgaloblishvili genome was sequenced using PacBio HiFi reads and assembled.

Historical terraced vineyards – heritage and nature conservation strategies

Historical terrace vineyards are simultaneously impressive documents of the human inclination to design, sites for the production of high quality wines and habitats for a rich variety of flora and fauna