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 legal concept of “cultural heritage” to refurbish the wine sector’s priorities

Following the latest oiv global report (april 26, 2024), the prevailing perception of wine consumption finds itself undergoing one of its most challenging adjustments. It’s plausible to anticipate a shift in the scope of pdo wines towards more human-centered products (wells and stiefel, 2019), necessitating the entire sector to adapt strategies to public interest patterns (touzeau, 2010: 17-31). Previously, a dominant notion of cultural property underscored the value of wine regions; the primary interest revolved around estate owners and retailers, along with vigneron tales.

Insights into the stable isotope ratio variability of hybrid grape varieties

The wine industry faces the consumer’s increasing demand for a sustainable and environmentally-friendly production [1]. This demand has been shared and boosted by the European Union within the European Green Deal in the Farm to Fork strategy that aims to reduce a 50% the pesticide utilisation in farming systems. Among the agronomical approaches so far proposed, the use of mould resitant hybrid varieties -based on crossings of Vitis vinifera with other Vitis spp [2]- with a high tolerance to the attack of vine patogens is gaining the vinegrowers attention and the production area is continuously increasing

The role of soil water holding capacity and plant water relations in zone/terroir expression

The spatial variability in soil type and depth and water holding capacity is very high in many viticultural regions of the world. Differences in rooting depths and water extraction profiles and their seasonal dynamics add additional variability and it is extremely difficult to deduct direct causal relationships between these factors and fruit

FIRST APPLICATION OF LACHANCEA THERMOTOLERANS IN THE FERMENTATION OF “VINO SANTO” AS BIOLOGICHAL ACIDIFIER.

The exploitation of secondary metabolic pathways of non-Saccharomyces yeasts is a promising approach to protect traditional wines from the ongoing climate change, which can alter their peculiar features by modifying the chemical composition of grape musts. In this regard, an interesting example is the sequential inoculum of Lachancea thermotolerans and Saccharomyces. Cerevisiae. The aim of the sequential inoculum is to increase titratable acidity by lactic acid accumulation, to lower pH and to reduce the alcohol and acetic acid content in wine.

Use of cyclodextrins to improve grape must fermentability thanks to their sequestering effect on medium-chain fatty acids

Cyclodextrins are complex cyclic oligosaccharides of glucose units. They are produced from the breakdown of starch by the enzymatic reaction of glucosyltransferase. The result is a ring-shaped molecule with a cavity with a hydrophilic outer part and a hydrophobic inner part. As a consequence of this cavity, cyclodextrin is able to form complexes with non-polar organic molecules [1,2].

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…

Quantitative assessment of must composition using benchtop NMR spectroscopy: comparative evaluation with FTIR and validation by reference

The foundation of wine production lies in the use of high-quality grapes. To produce wines that meet the highest standards, a fast and reliable analytical assessment of grape quality is essential. Many wineries currently employ Fourier-Transform Middle-Infrared Spectroscopy (FTIR) for this purpose.

Water status response of Vitis vinifera L. cv Cabernet Sauvignon during the first years within the long-term VineyardFACE (Free Air Carbon dioxide Enrichment) study 

Understanding grapevine responses to increasing atmospheric CO2 (aCO2) concentrations is crucial for assessing the impact of climate change on viticulture. Previously, at the VineyardFACE (Free Air Carbon dioxide Enrichment) experiment in Geisenheim, leaf gas exchange measurements were made as Vitis vinifera cv. Cabernet Sauvignon established from planting (2014 to 2016) under aCO2 or elevated CO2 (eCO2, aCO2 + 20%) concentrations. Contrary to many preceding observations with grapevines and other perennial plant species the young vines showed an increased intrinsic water use efficiency (WUEi) that was mainly associated with an increase in net assimilation (A) rather than a decrease in stomatal conductance (gs) under eCO2.

How do KOCs influence wine consumers’ decisions? Based on NLP analysis and questionnaire surveys on Xiaohongshu

In China’s social media-driven marketing landscape, user-generated content (UGC) plays a pivotal role in brand communication and consumer decision-making.

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.

A multidisciplinary approach to assess the impact of future drought scenarios on vineyard ecosystems

Drought events can strongly affect grapevine and berry physiology and subsequent wine quality, as widely demonstrated in controlled experiments.