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 temporal sensory interaction between 3-Mercaptohexanol, 3-Mercaptohexyl Acetate and Athanethiol using trata

Volatile sulphur compounds are a group of impact odorants with low odour thresholds that can contribute both positively and negatively to wine aroma. The varietal thiols, 3MH and 3MHA, are known to contribute positive tropical aromas to white wines and are most abundant in Sauvignon Blanc wines. The group of compounds contributing negative aromas are known as reductive sulphur compounds (RSCs) as they add a reductive aroma of asparagus, cooked vegetables and rotten egg to wines. All these compounds play a part in and are a result of the sulphur pathway in the yeast cell during fermentation and therefore attempting to increase the concentration of the varietal thiols may directly influence the concentration of the RSCs. The varietal thiols and the low molecular weight RSCs are highly volatile and therefore their sensory perception can change rapidly over time.

Bentonite fining in cold wines: prediction tests, reduced efficiency and possibilities to avoid additional fining treatments

Bentonite fining is widely used to prevent protein haze in white wines. Most wineries use laboratory-scale fining trials to define the appropriate amount of bentonite to be used in the cellar. Those pre-tests need to mimic as much as possible the industrial scale fining procedure to determine the exact amount of bentonite necessary for protein stability. Nevertheless it is frequent that, after fining with the recommended amount of bentonite, wines appear still unstable and need an additional fining treatment. It remains a major challenge to understand why the same wine, fined with the same dosage of the same bentonite, achieves stability in the lab, but not in the cellar.

Grape variety identification and detection of terroir effects from satellite images

Satellite images are used to determine the reflectance dependency to wavelength in different grape varieties (Cabernet-Sauvignon, Merlot, Pinot Noir, and Chardonnay). The terroir influence is investigated through study of vineyards in France, Brazil and Chile.

Viticultural parameters and enological performance of six Merlot clones in two contrasting vintages

Vitis vinifera L. and other Vitis have high genetic variations for cultivars or varieties. Many countries carried out strong efforts creating new clones of varieties, mainly focusing on plants free of viruses and other grapevine diseases, but also on different agronomical and enological characteristics of the plants. The aim of this study was to evaluate six clones of Merlot in the traditional viticulture of southeastern Brazil, focusing on distinct characteristics of yield, enological potential of grapes and wine typicality, in order to improve wine quality.

Sensory characterisation and consumer perspectives of Australian Cabernet Sauvignon wine typicity

Aim: To identify the sensory attributes responsible for the typicity of Cabernet Sauvignon wines from three Australian Geographical Indications (GIs) and to explore consumer purchase behaviour and preference with regard to regional wines.

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…

Effet de l’ombrage respectif des ceps et des grappes de Muscat sur leurs teneurs en composés volatils libres et glycosyles et en précurseurs d’aromes carotenoïdiques

Le Muscat de Frontignan est bien connu pour ses fortes teneurs en composés terpéniques et par l’odeur florale et fruitée que ces composés confèrent aux vins qui en sont issus (1,2).

Genetics of adventitious root formation in grapevines

Commercial grapevine propagation relies on the ability of dormant wood material to develop adventitious roots.

Mechanistic insights into the bioavailability of oleocanthal and oleacein from olive oil in presence of wine active peptides and amino acids

Oleocanthal (OC) and oleacein (OL) are highly bioactive secoiridoids found in olive oil at elevated concentrations, especially when it is produced from unripe olives (Olea europaea L.). Both compounds have been correlated with strong activities against serious diseases through recent clinical trials. The most important clinical trials have been performed in patients against chronic lymphocytic

Geologic and geomorphologic features applied for identification of wine terroir units by digital image processing, spectroradiometric and GIS techniques in Encruzilhada do Sul, RS, Brazil

Results in the characterization of a new wine terroir unit in south Brazil are reported. Presently, several areas in Brazil are being studied, in an effort to define new wine terroirs and improve the quality of Brazilian wines.

Impact of cover crop in vineyard on the musts volatile profile of Vitis vinifera L. Cv Syrah

rape aromatic characteristics are very important for the production of quality wines. The concentrations of volatile compounds in grape berries from vines with cover crops have been scarcely studied.