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…

La place du terroir dans le processus de patrimonialisation : l’exemple des paysages culturels viticoles du patrimoine mondial de l’Unesco

Eleven wine-growing sites are now on the UNESCO World Heritage List as Cultural Landscapes. If the viticultural character of these sites constitutes the main argument for the demonstration of their heritage value, the terroir and its biophysical and environmental characteristics tend however to appear in a minor mode compared to the aesthetic and cultural dimensions. In other words, the “specific characteristics of the soil, topography, climate, landscape and biodiversity” (OIV definition) are most often used as descriptive elements in the presentation of the sites, but it is more the aesthetic, historical,

Oak Tannin and Unoaked and Oaked Wine Extracts Influence Gene Expression in HepaRG Human Liver Cells

Previous work from our laboratory has shown that both a purified toasted oak powder and extracts made from unoaked and oaked red wines influenced physiological parameters, metabolism and hepatic gene expression in high-fat fed C57/BL6J male mice (Luo et al., 2020).  Impacted pathways included glucose metabolism, liver fat accumulation, markers of chronic inflammation, and expression of the Gsta1 mRNA.  

Field-grown Sauvignon Blanc berries react to increased exposure by controlling antioxidant homeostasis and displaying UV acclimation responses that are influenced by the level of ambient light

Leaf removal in the bunch zone is a common viticultural practice with several objectives, yet it has been difficult to conclusively link the physiological mechanism(s) and metabolic berry impact to this widely practiced treatment. We used a field-omics approach1 in a Sauvignon blanc high altitude model vineyard, showing that the early leaf removal in the bunch zone caused quantifiable and stable responses (over years) in the microclimate where the main perturbation was increased exposure. We provide an explanation for how leaf removal leads to the shifts in grape metabolites typically linked to this treatment and confirm anecdotal evidence and previous reports that leaf removal treatment at an early stage of berry development affects “quality-associated” metabolites (monoterpenes and norisoprenoids).

The use of remote sensing for intra-block vineyard management

L’unité de gestion technique d’un vignoble est aujourd’hui la parcelle. Néanmoins, au sein d’une même parcelle, la variabilité de l’expression végétative et de la constitution des raisins à maturité, peut être grande, en particulier à cause d’une hétérogénéité du sol.

Global warming effects on grape growing climate zones within the Rioja Appllation (DOCa Rioja) in north Spain

Aims: The aims of this work were (1) to assess the changes in some of the main bioclimatic indices used for climate viticultural zoning within the Rioja Appellation area in the north of Spain between 1950-2014 (60 years), and (2) to carry out a comprehensive sociological evaluation among grapegrowers and winemakers of this region, to better understand the impact of climate change on their activity, their degree of concern about it and the potential adaptation measures they would be willing to adopt to cope with it in future years.

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…

Ability of Saccharomyces cerevisiae strains to modulate the aroma of albariño wines

The objective of the present work is to evaluate the impact of three S. cerevisiae strains on the comprehensive aroma profile of Albariño wine along its shelf life.

Approche méthodologique concernant une caractérisation sensorielle de vins rouges de l’Anjou

Face à une concurrence de plus en plus rude entre pays producteurs, le vignoble de l’Anjou, déjà riche par sa diversité, souhaite renforcer sa logique de vins d’ A.O.C., notamment au travers de ses vins rouges.

Characterizing graft union formation in different scion/rootstock combinations of grapevine 

In most viticultural regions, grapevines are cultivated grafted, employing either hybrid or pure species of various American Vitis spp., such as V. berlandieri, V. rupestris, and V. riparia, as grapevine rootstocks. These rootstocks play a crucial role in providing resistance to the Phylloxera insect pest. Beyond Phylloxera resistance, it is desirable for grapevine rootstocks to exhibit resistance to other soil-borne pathogens and adaptability to abiotic stress conditions. The introduction of new rootstocks holds promise for adapting agriculture to climate change without altering the characteristics of the final harvested product.

EVALUATION OF INDIGENOUS SACCHAROMYCES CEREVISIAE ISOLATES FOR THEIR POTENTIAL USE AS FERMENTATION STARTERS IN ASSYRTIKO WINE

Assyrtiko is a rare ancient grape variety that constitutes one of the most popular in Greece. The objective of the current research was to evaluate indigenous Saccharomyces cerevisiae isolates as fermentation starters and also test the possible strain impact on volatile profile of Assyrtiko wine. 163 S. cerevisiae isolates, which were previously selected from spontaneous alcoholic fermentation, were identified at strain level by interdelta-PCR genomic fingerprinting. Yeasts strains were examined for their fermentative capacity in laboratory scale fermentation on pasteurized Assyrtiko grape must.

Wine industry, digital transformation, and sustainability: a systematic literature 

This paper aims to (i) identify the state of the art regarding digital transformation in the transition to sustainability in the wine industry, (ii) analyze the adoption of digital technologies at different stages of the winemaking process and their contribution to the triple bottom line of sustainability, and (iii) present a research agenda that facilitates the development of the field, providing contributions to both literature and managerial practice.