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…

ABOUT THE ROLE PLAYED BY THE DIFFERENT POLYPHENOLS ON OXYGEN CONSUMPTION AND ON THE ACCUMULATION OF ACETALDEHYDE ANDSTRECKER ALDEHYDES DURING WINE OXIDATION

In a previous work1, it was suggested that the different contents in delphinidin and catechin of the grapes were determinant on the O2 consumption and Strecker aldehyde (SAs) accumulation rates. Higher delphinidin seemed to be related to a faster O2 consumption and a smaller SAs accumulation rate, and the opposite was observed regarding catechin.
In the present paper, these observations were fully corroborated by adding synthetic delphinidin to a wine model containing polyphenolic fractions (PFs) extracted from garnacha and synthetic catechin to a wine model containing PF extracted from tempranillo: The delphinin-containing garnacha model consumed O₂ significantly faster and accumulated significantly smaller amounts of SAs than the original garnacha model, and the catechin-containing tempranillo model, consumed O2 significantly slower and accumulated significantly higher amounts of SAs than the original tempranillo model.

Rare earth elements distribution in grape berries

Rare Earth Elements (REEs) include 15 lanthanides, yttrium and scandium. Their occurrence in soil and plants seems to be closely tied to the geological composition of the underlying mother rock, to the physical and chemical properties of the soil and to the specific ability of the plant to take up and accumulate these microelements.

Manipulating grapevine bud fruitfulness

Bud fruitfulness is a key component of reproductive performance of grapevine. It plays a significant role in annual yield variation of vineyards as it is a prerequisite of crop production in the following season. Various exogenous and endogenous factors influencing the development of inflorescence primordia (IP) have been studied. However, the research on molecular genetic control of bud fruitfulness, especially how it interacts with environmental factors is still lacking. This study aims to investigate the molecular mechanism of effects of temperature and light on grapevine bud fruitfulness during initiation and differentiation of IP.

Decline of rootstock-mediated physiological responses in Tempranillo grapevines by prolonged extreme conditions

Agriculture faces many global warming challenges especially in the Mediterranean region. Many strategies have been proposed in viticulture to manage global warming. Rootstocks are among them since they may affect water uptake and the scion’s performance.
The study conducted in La Rioja, Spain, aimed to investigate the impact of different rootstocks (1103P and 161-49C) on the performance of the Tempranillo grapevine scion over a three-day cycles under drought and extreme conditions, specifically during a heatwave in July 2022, with maximum air temperatures up to 40ºC and average daily temperatures of 29.1ºC.

INFLUENCE OF CHITOSAN, ABSCISIC ACID AND BENZOTHIADIAZOLE TREATMENTS ON SAVVATIANO (VITIS VINIFERA L.) WINES VOLATILE COMPOSITION PROFILE

In the last decades the use of bioestimulants in viticulture have been promoted as alternative to conven- tional pesticides. Moreover, as bioestimulants promote the biosynthesis of secondary metabolites in grape berries, several studies had investigated their influence on the accumulation of phenolic com- pounds (Monteiro et al., 2022). However, few studies, so far, are focused on the accumulation of the vo- latile compounds and their impact on the produced wines (Giménez-Bañón et al., 2022; Gomez- Plaza et al., 2012; Ruiz Garcia et al., 2014).
This study was conducted in a single vineyard of white autochthonous grapevine variety Savvatia- no (Vitis vinifera L.) in Muses Valley (Askri, Viotia, Greece). Chitosan (CHT), Abscisic Acid (ABA) and Benzothiadiazole (BTH) were applied.

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…

Influence of oak species on the differentiation of aged brandies using chemometrics approach based on phenolic compounds UHPLC fingerprints

Oak is the main material used in cooperage for making barrels and wood chips destined to aged spirits and wines. Quercus alba L., Quercus petraea L. and Quercus robur L. are three of the most commonly used oak species in cooperage companies.

Developing a multi-hazard risk index-based insurance for viticulture under climate change

Climate change is increasing the frequency and severity of environmental hazards (e.g., prolonged drought), and even non-extreme climate events (e.g., a period of slightly warmer temperatures) can lead to extreme impacts when they occur simultaneously with other (non-extreme) events.

Contaminations croisées avec les produits phytosanitaires dans les vins bio. Sources potentielles et mesures de prévention.

Organic wines, although resulting from a production method based on the non-use of synthetic phytosanitary products, are not always free of residues. These residues can result from cross-contamination during production in the field or in the cellar, during the production or aging of the wine. In recent years, with the improvement of analysis techniques, a molecule, phosphonic acid, the main metabolite of fosetyl-al (banned in organic farming) is regularly quantified in organic wines and its origin is not clearly identified.

Interaction between commercial mannoproteins and phenolic compounds of two red wines from different Portuguese grape cultivars

The interaction between mannoproteins and wine phenolic compounds is a subject of great interest as some studies show the possible impact in color stability and an improvement in the sensory characteristics namely the reduction of red wine astringency.

Development of a new indicator of grape skin ripening in relation to Botrytis cinerea susceptibility

The bunch rot induced by Botrytis cinerea is an important disease of grapevine that causes a diminution of grape quality and a considerable yield loss leading to an economic loss