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…

Towards an ecological architecture inspired by underground cellars: An example of the thermal inertia of Moldovan underground cellars and new geothermal and Canadian well approaches

The search for underground shelters is one of the oldest forms of human habitation, providing refuge in extreme environments such as deserts and polar regions.

Il paesaggio delle alberate aversane ed il vino Asprinio

Nel corso del 2009, in alcuni vigneti allevati ad alberata in provincia di Caserta (Italia), è stata avviata una ricerca per valutare la variabilità genetica della popolazione del vitigno ‘Asprinio’, la condizione sanitaria delle piante e le caratteristiche del vino sia rispetto alla forma di allevamento (alberata tradizionale e controspalliera) che all’altezza della fascia produttiva.

Il piano regolatore delle città’ del vino: aspetti urbanistici, economici e turistici

[lwp_divi_breadcrumbs home_text="IVES" use_before_icon="on" before_icon="||divi||400" module_id="publication-ariane" _builder_version="4.19.4" _module_preset="default" module_text_align="center" text_orientation="center" custom_margin="65px||18px||false|false"...

Antociani ed acidi cinnamici per la caratterizzazione di vitigni in zone diverse della Toscana

The phenolic compounds (cathechins, cynnamic acids, anthocyanidins) in wines made from 6 vine-varieties (Sangiovese, Cabernet S., Nero d’Avola, Foglia Tonda, Pinot N., Mazzese) grown in 4 different pedoclimatic zones of Tuscany (Arezzo, Grosseto, Pisa and Lucca) have been analyzed by HPLC.

Effect of pre-fermentative strategies on the polysaccharide composition of must and white wines

Among the macromolecules of enological interest in white wines, much attention has been paid to polysaccharides.

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…

Vineyard yield estimation using image analysis: assessing bunch occlusions and its dependency on fruiting zone canopy features

Performing accurate vineyard yield estimation is of upmost importance as it provides important benefits to the whole vine and wine industry. Recently, image-analysis approaches have been explored to address this issue however this approach has as main challenge the bunch occlusion, mostly by vegetation but also by neighboring bunches. The present work aims at assessing the magnitude of bunch occlusion by neighboring bunches and to evaluate its dependency on a selection of vegetative and reproductive vine parameters assessed at fruiting zone. Forty vine segments (1 m) of two vineyard plots of the white cultivars ‘Alvarinho’ and ‘Arinto’ were assessed for vegetative and reproductive features at fruiting zone and imaged with a 2D camera.

THE EFFECT OF PRE-FERMENTATIVE GLYPHOSATE ADDITION ON THE METABOLITE PROFILE OF WINE

The synthetic herbicide glyphosate has been used extensively in viticulture over many decades to combat weeds. Despite this, the possible influence of residual glyphosate on both the alcoholic fermentation of grape juice and the subsequent metabolite profile of wines has not been investigated. In this study, Pinot noir juice supplemented with different concentrations of glyphosate (0 µg L-1, 10 µg L-1 and 1000 µg L-1) was fermented with commercial Saccharomyces cerevisiae yeast strains. Using a combination of analytical methods, 80 metabolites were quantified in the resulting wines.

Toasted Vine-Shoots As An Alternative Enological Tool. Impact On The Sensory Profile Of Tempranillo Wines

The use of toasted vine-shoots as an alternative enological tool to make differentiated wines has generated interest among researchers and wineries. However, the evolution of these wines in bottle and the effect on the sensory profile has not been studied so far.

Impact of grapevine rootstock genotypes on nitrogen status of the scion and phenolic composition in Pinot noir berries and wine

Context and purpose of the study. Nitrogen (N) limitation enhances the production of phenolic compounds in grapes due to the downregulation of the flavonoid biosynthesis pathway.

Preserving wine typicity in a climate change scenario: Examples from the Willamette Valley, Oregon

Aims: Wine typicity is defined as a reflection of varietal origins, cultures and traditions of the wine. These aspects are many times also extremely important when considering a wines quality. However, as climate change occurs the typicity of wines may also change. With the long history of winemaking it is possible to define a wines typicity and how it has changed as climate alters.