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…

Management of varietal thiols in white and rosé wines using biotechnical tools

The present study evaluates the effect of prefermentative maceration enzymes and yeast autolysate on the concentration of conjugated precursors and volatile thiols, respectively.Sauvignon blanc and Merlot grapes underwent skin-contact maceration with or without pectolytic enzymes, for the production of white and rosé wines

Uve e vini in vulcaniti basiche anorogeniche dei lessini meridionali, impronta petrochimica e assimilazione di metalli pesanti

Nel 2009 sono stati prelevati e analizzati mediante XRF (X-ray fluorescence) campioni di suolo, in vigneti sperimentali siti nelle province di Vicenza e di Ancona. Sono stati inoltre determinati in 2 campioni di mosto e 2 di vino delle varietà Verdicchio e Refosco dal peduncolo rosso, ed in 2 di uva Refosco dal peduncolo rosso, gli elementi in traccia mediante ICP-MS (Inductively coupled plasma-mass spectrometry).

Effect of Botrytis cinerea and esca on phenolic composition of berries and wines

This study showed that Botrytis cinerea could degrade the phenolic compounds by its enzymatic activity. It led to a diminution of skin’s anthocyanins from 20 % to 50 % and an increase level up to 40 % of individual proanthocyanins, 30 % of the %G and 25% of the %P.

Volatile Organic Compound markers of Botrytis cinerea infection in artificially inoculated intact grape berries

The addition of partially dehydrated grapes to enrich must composition for producing complex dry/sweet wines represents a traditional practice in several regions of the world. However, the environmental conditions of dehydration chambers may facilitate the infection of Botrytis cinerea Pers. by promoting disease and provoking large grape losses. B. cinerea attack can induce alterations in the profile of volatile organic compounds (VOCs), which could be detected by sensors specifically trained to detect infection/disease-related compounds. These sensors could facilitate the early detection of the infection, consequently allowing to adjust some dehydration parameters.

Bioprotective non-Saccharomyces yeast as an alternative to sulfites for the winemaking process

Sulfur dioxide (SO2) is used in winemaking due of its antioxidant, antioxydasic and antiseptic properties. Excessive amount of SO2 can negatively impact wine sensory perception and be detrimental for health. Agri-food industries are more transparent towards consumers concerning addition of sulfites, and oenology is no exception in this clairvoyance. As a consequence, the increase of consumers preference for wine with low or absent of sulfites addition is notorious. In this context, the impact of low/zero sulfites winemaking process on the microbial community should be evaluated. Moreover, microbial agents corresponding to bioprotective cultures represent a growing interest as an alternative to sulfites preservation in the early stages of vinification. However, scientific studies conducted to demonstrate their real effect are almost rare.

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…

Towards a relationship between institutional clonal selection, mass selection and private clonal selection of grapevine cultivars

Each grape cultivar is composed of a population of individuals that are genetically different. Clonal selection has allowed the purification and improvement of the global quality

Oenococcus oeni clonal diversity in the carbonic maceration winemaking

This essay was aimed to describe the clonal diversity of Oenococcus oeni in the malolactic fermentation of the carbonic maceration (CM) winemaking. The free and the pressed liquids from CM were sampled and compared to the wine from a standard winemaking with previous destemming and crushing (DC) of grapes [1]. O. oeni strain typification was performed by PFGE as González-Arenzana et al. described (2014) [2]. Results showed that 13 genotypes, referred as to letters, were distinguished from the 49 isolated strains, meaning the genotype “a” the 27%, the “b” the 14%, the “c” the 12%, the “d and e” the 10 % each other, and the remaining ones less than the 8% each one.

Non-invasive quantification of phenol content during red wine fermentations

Phenolic compounds are responsible for the most important red wine quality attributes. Anthocyanins and tannins play crucial roles in color and mouthfeel properties of red wines. Phenolic analysis in the winery is hindered by analytical constrains.

Genotypic differences in early-stage root architectural traits and consequences for water uptake in three grapevine rootstocks differing in drought tolerance

Root architecture (RSA), the spatial-temporal arrangement of a root system in soil, is essential for edaphic resources acquisition by the plant, and thus contributes largely to its productivity and adaptation to environmental stresses, particularly soil water deficit. In grafted grapevine, while the degree of drought tolerance induced by the rootstock has been well documented in the vineyard, information about the underlying physiological processes, particularly at the root level, is scarce, due to the inherent difficulties in observing large root systems in situ. The aims of this study were (i) to determine the phenotypic differences in traits related to root distribution and morphology along the substrate profile in different Vitis rootstocks during early growth, (ii) to assess the plasticity of these traits to soil water deficit and (iii) to quantify their relationships with plant water uptake.

Influence of withering on valpolicella docgs grapes volatile composition

The blend of grapes used in the production of the four Valpolicella PDOs red wines, namely Valpolicella, Valpolicella Classico Superiore, Recioto della Valpolicella and Amarone della Valpolicella is quite unique, and includes two main varieties Corvina and Corvinone, and other minor varieties. To a very large extent all these grapes are only grown in the province of Verona. One of the main characteristics of Valpolicella is the use of grapes that are submitted to post-harvest withering. The aim of this study was therefore to evaluate the evolution of the free and glycosidically-bound volatile compounds in Corvina and Corvinone grapes under real production conditions.