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…

From the “climats de Bourgogne” to the terroir in bottles

From a chemical composition point of view, wine is the result of complex interplays between environmental, genetic and human factors. The notion of terroir in viticulture involves the vine and its environment, including phenology, geography, geology, pedology and local climate of a vineyard, along with human inputs.

Influence of preflowering basal leaf removal on aromatic composition of cv. Tempranillo wine from semiarid climate (Extremadura Western Spain)

Abstract In this work the effects of early leaf removal performed manually at preflowering phenological stage, on the volatile composition of Tempranillo (Vitis vinifera L.) wines were studied. From 2009-2011 vintages 34 wine volatile compounds were identified and quantified by gas chromatography-mass spectrometry (GC-MS) where early leaf removal only modified 25 of them. The total C6 compounds, acetates and volatiles acids (with exception of isobutyric acid) were affected by defoliation, whereas alcohols and esters showed a minor effect. Furthermore the vintage effect also was shown.

Temperature-based phenology modelling for the grapevine 

Historical phenology records have indicated that advances in key developmental stages such as budburst, flowering and veraison are linked to increasing temperature caused by climate change. Using phenological models the timing of grapevine development in response to temperature can be characterized and projected in response to future climate scenarios.
We explore the development and use of grapevine phenological models and highlight several applications of models to characterize the timing of key stages of development of varieties, within and between regions, and the result of projections under different climate change scenarios.

Effect of two contrasting soils on grape and wine sensory characteristics in Shiraz

Aims: Berry composition and wine sensory characteristics reflect the origin of grape production and seasonal climatic conditions. The aim of this study was to compare berry and wine sensory characteristics from two contrasting soil types where the vineyard climate, geography, topography, vine and management factors were not different.

EFFECT OF DIFFERENT VITICULTURAL AND ENOLOGICAL PRACTICES ON THE PHENOLIC COMPOSITION OF RED WINES

Global climate change is exerting a notable influence on viticulture sector and grape composition. The increase in temperature and the changes in rainfall pattern are causing a gap between phenolic and technological grape maturities [1]. As a result, the composition of grapes at harvest time and, consequently, that of wines are being affected, especially with regards to phenolic composition. Hence, wine quality is decreasing due to changes in the organoleptic properties, such as color and astringency, making necessary to implement new adaptive technologies in wineries to modulate these properties in order to improve wine quality.

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…

Sensitivity of vis‐nir spectral indices to detect nitrogen deficiency and canopy function in cv. Barbera (Vitis vinifera L.) Grapevines

Precision nutrient management in viticulture can be addressed on the basis of a spatial characterization of within‐vineyard vine

Investigation of the effect of gelatine and egg albumin fining and cross-flow microfiltration on the phenolic composition of Pinotage red wine

Results indicated that cross-flow microfiltration removed similarly to fining treatments the most astringent tannins, but cross-flow microfiltration also removed up to 14 % more colour. RP-HPLC and spectrophotometric results showed that egg albumin is a softer fining treatment compared to gelatine and cross-flow microfiltration.

Biotype diversity within the autochthonous ‘Bobal’ grapevine variety

Bobal is the second most widely grown Spanish red grape variety (54,165 has), mainly cultivated in the Valencian Community and especially, in Utiel-Requena region (about 67% of 34,000 has). In this study, agronomic and enological parameters were determined in 98 biotypes selected during 2018 and 2019 in more than 50 vineyards over 50 years-old in the Utiel-Requena region. Moreover, a multi-criteria approach considering temperature and rainfall (Fig. 1A), among other parameters, was made to establish three different zones within the region (Fig. 1B), where in the future the selected biotypes will evaluated. In fact, in 2020, 4 replicates and 12 vines per biotype were planted in an experimental vineyard to preserve this important intra-cultivar diversity.

Grapevine Shiraz disease-associated viruses lead to yield losses by altering transcription of genes

Context and Purpose of Study. Grapevine Shiraz disease (SD), which is associated with Grapevine Virus A (GVA), is one of the highly destructive diseases affecting Australian and South African vineyards.

Isolated Antarctic soil yeasts with fermentative capacity with potential use in the wine industry

The wine industry is currently on the search for new aromas and less browning in their products. In the improvement process of wine, lower fermentation temperatures have been considered, however, the yeasts in the market cannot tolerate such temperatures