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…

Insulative effects of vine shelters may impact growth potential and cold hardiness of young vines

Context and purpose of the study. The seasons immediately following planting are key growth stages where young vines are particularly susceptible to various forms of damage.

Towards the definition of a terroir of grape dehydration for the production of ‘Passito’ wines in Valpolicella (Italy)

Aim: The aim of this study was to investigate the relationship between the molecular response of grapes during postharvest dehydration and the specific environment of two naturally ventilated rooms (called ‘fruttai’), located in two different sites in Valpolicella

Exploring the plasticity of the grapevine drought physiology

Grapevine response to water deficit has been extensively studied. Nevertheless, debate still exists regarding some physiology adoption under drought

Microbiome, disease-resistant varieties, and wine quality

The development of interspecific hybrid varieties (ihvs) resistant to diseases such as powdery mildew and downy mildew allows for a decrease in the use of inputs in vineyards. In this pers-pective, ihvs represent a response to societal demand for reducing environmental impact and are increasingly used in viticulture. At the same time, wines resulting from so-called sponta-neous fermentations, based on indigenous flora, have recently gained popularity.

Barrel-to-Barrel Variation of Color and Phenolic Composition in Barrel-Aged Red Wine

Tangible variation of sensory characteristics is often perceived in wine aged in similar barrels. This variation is mostly explained by differences in the wood chemical composition, and in the production of the barrels. Despite these facts, the literature concerning barrel-to-barrel variation and its effect on wine sensory and chemical characteristics is very scarce [1]. In this study, the barrel-to-barrel variation in barrel-aged wines was examined in respect of the most important phenolic compounds of oenological interest and chromatic characteristics, considering both the effects of the (individual) barrel and cooperage. A red wine was aged in 49 new medium-toasted oak (Quercus petraea) barrels, from four cooperages, for 12 months

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…

Improving grapevine cloning material of Welshriesling by comprehensive analysis

The important grape variety Welschriesling for Austrian and Southeast European viticulture has been selectively bred over the years for improving some quantitative traits. Collected genotypes as well as the local clones were examined from agricultural, analytical, sensory, and genetic perspectives.

A survey on the rotundone content of 18 grape varieties sourced from a germplasm 

Rotundone, the pepper aroma compound, has been detected in wines made from a large number of grape varieties. However, given the fact that analyzed wines were sourced from different winegrowing regions and seasons, made using different winemaking techniques and at different scales, it remains difficult to assess the real variety potential to produce rotundone.

Current climate change in the Oplenac wine-growing district (Serbia)

Serbian autochthonous vine varieties Smederevka (for white wines) and Prokupac (for rosé and red wines) are the primary representatives of typical characteristics of wines and terroir of numerous wine-growing areas in Serbia. In the past, these varieties were the leading vine varieties, however, as the result of globalization of winemaking and the trend of consumption of wines from widely prevalent vine varieties, they were replaced by introduced international varieties. Smederevka and Prokupac vine varieties are characterized by later time of grape ripening, and relative sensitivity to low temperatures. Climate conditions can be a restrictive factor for production of high-quality grapes and wine and for the spatial spreading of these varieties in hilly continental wine-growing areas.
This paper focuses on the spatial analysis of changes of main climate parameters, in particular, analysis of viticultural bioclimatic indices that were determined for the purposes of viticulture zoning of wine-growing areas in the period 1961-2010, and those same parameters determined for the current, that is, referential climate period (1988-2017). Results of the research, that is, analysis of climate changes indicate that the majority of examined climate parameters in the Oplenac wine-growing district improved from the perspective of Smederevka and Prokupac vine varieties. These studies of climate conditions indicate that changes of analyzed climate parameters, that is, bioclimatic indices will be favorable for cultivation of varieties with later grape ripening times and those more sensitive to low temperatures, such as the autochthonous vine varieties Smederevka and Prokupac, therefore, it is recommended to producers to more actively plant vineyards with these varieties in the territory of the Oplenac wine-growing district.

Influence of harvest time and withering length combination on reinforced Nebbiolo wines: phenolic composition, colour traits, and sensory profile

Sforzato di Valtellina DOCG is a reinforced dry red wine produced in the mountain area of Valtellina alpine valley (North Italy), using ‘Nebbiolo’ grapes that undergo a withering process. This process impacts on the grape composition due to a sugar concentration and changes in secondary metabolism influencing volatile organic compounds (VOCs) and polyphenols.

Gastrointestinal digestion of wine sulphites and their effects on human gut microbiota

Sulphites are by far the most widely used additive in the wine industry. In relation to health, the interaction of sulphites with the gut microbiota has not been addressed so far. Following the consumption of wine and other sulphite-containing foods, the gastrointestinal tract and the microbiome are one of the first barriers that these compounds face in the human organism. In this study, we used a previously validated gastrointestinal digestion model (SIMGI®) [1,2] to evaluate the effect of intestinal digestion of wine sulphites on the gut microbiome.