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…

Solid Rectified Concentrated grape Must (SRCM) in sparkling wines production: studying the sensory impact of an innovative sugar substrate

The production of sparkling wines requires sugars for the second fermentation. The Solid Rectified Concentrated Must (SRCM) is a water free crystalline form of grape sugar, offering a purer, more stable, and easier-to-use alternative to the liquid Rectified Concentrated Must (RCM).

Raffinose: a sweet solution for grapevine drought tolerance

Water tolerance in plants is often associated with the accumulation of osmotic protectants, which are secondary metabolites that can help the plant to cope with water stress. One of the key osmotic protectants is a sugar called Raffinose, which is synthesized by a family of enzymes called Raffinose synthases. In this work, we focused on one of these enzymes, VviRAF2, which is a gene that shows different expression levels and genetic variants (SNPs) among different grapevine cultivars, ranging from tolerant to susceptible to water stress, and the transcription factors that may regulate the expression of this gene family.

Prospects for enlarging of microzone Manavi in the East Georgia

The experimental studies conducted in the eastern Georgia in Sagarejo administrative district on the foothills of the southern slope of Tsiv-Gombori range reveal the possibility of enlarging Manavi traditional specific zone to the north-west (from Giorgitsminda to Khashmi), at 500-750 m above sea level.

Where the sky is no limit — The transformation of wine marketing through text-to-video generation AI model

The introduction of ai-driven tools in digital content creation represents a significant shift in the landscape of marketing, particularly for industries reliant on rich visual storytelling such as the wine sector. The development of ai models like openai’s sora, runway’s gen-2 or google’s lumiere, which can generate realistic video content from textual descriptions, offers promising new avenues for enhancing brand narrative and consumer engagement. This research explores the potential of text-to-video (t2v) ai models to revolutionize wine marketing by creating dynamic, engaging content that captures the essence of vineyards and their products without the need for traditional video production processes.

How much does the soil, climate and viticultural practices contribute to the variability of the terroir expression?

When considering the application of a systemic approach to assess the intrinsic complexity of agricultural production, the following question immediately arises

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…

A general phenological model for characterising grape vine flowering and véraison

The timing of phenology is critical if grape quality potential is to be optimized. Phenological process based models are used to predict phenology. In this study, three different models

Genetic traceability of the varietal origin of wines: a robust application for must and wines during alcoholic fermentation

Industry and regulatory agencies have developed regulations to ensure authenticity and compliance with wine composition limits. However, this can be truncated by the absence of simple and robust analytical methodologies, uninfluenced by the environment, different oenological techniques and cultural practices. Genetic fingerprinting is the most powerful tool for unequivocal varietal identification; it is not affected by the environment or agronomic practices; however, its usefulness in musts and wines has been controversial and there is currently no routine certification of varietal origin based on DNA analysis.

Temperature variability assessment at vineyard scale: control of data accuracy and data processing protocol

Climatic variability studies at fine scale have been developed in recent years with the reduction of material cost and the development of competitive miniaturized sensors. This work is forming part the LIFE-ADVICLIM project, of which one of the objectives is to model spatial temperature variability at vineyard scale. In the Bordeaux pilot site, a large network of data loggers has been set up to record temperature close to the vine canopy. The reduced distance between plant foliage and measurement equipment raises specific issues and leads to an increased rate of outliers compared to data retrieved from classical weather stations. Some of these were detected during data analysis, but others could not be easily identified. The present study aims to address the issue of data quality control and provide recommendations for data processing in climatic studies at fine scale.

Enological technics to enhance the aromatic qualities of white spirits 

Eugenol has been identified as a quality marker in armagnac white spirits. In particular, those produced from the Baco blanc variety, the only hybrid variety authorised in a French PDO, bred since 1898 from noah (vitis labrusca x v.riparia) and folle blanche (v. Vinifera). The varietal compound of Baco blanc, eugenol has many original properties.

Multisensory experiential wine marketing

Interest in the pairing, or matching, of wine with music goes way back, with commentators initially using musical metaphors merely to describe the wines that they were writing about. More recently, however, this has transformed into a growing range of multisensory tasting events in which wine and music are deliberately paired to assess, or increasingly to illustrate, the impact of the latter on