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…

Direct-injection HPLC for simultaneous determination of individual and total polyphenols in red wines: validation of the method

Polyphenols are very important compounds of red wines, serving as essential bioactive components and playing an important role in sensory properties. The determination of individual phenolic compounds in red wine is commonly performed by HPLC analysis, while the total polyphenols are quantified by spectrophotometric methods, usually by the method of absorbance at 280 nm (index of ribéreau-gayon) or the method of index of folin-ciocalteu. In this work, we pioneeringly proposed a new and fast method for simultaneous determination of individual and total polyphenols in red wines by direct-injection HPLC without sample preparation.

How artificial intelligence (AI) is helping winegrowers to deal with adversity from climate change

Artificial intelligence (AI) for winegrowers refers to robotics, smart sensor technology, and machine learning applied to solve climate change problems. Our research group has developed novel technology based on AI in the vineyard to monitor vineyard growth using computer vision analysis (VitiCanopy App) and grape maturity based on berry cell death to predict flavor and aroma profiles of berries and final wines.

Plant fibers in comparison with other fining agents for the re-duction of pesticide residues and the effect on the volitile profile of Austrian white and red wines.

Pesticide residues in Austrian wines have so far been poorly documented. In 250 wines, 33 grape musts and 45 musts in fermentation, no limit values were exceeded, but in some cases high lev-els (>0.100 mg/l) of single residues were found, meaning that a reduction of these levels before bottling could make sense. In the course of this study, a white and a red wine were spiked with a mix of 23 pesticide residues from the group of fungicides (including botryticides), herbicides and insecticides. The influence of the following treatments on residue concentrations and volatile profiles were investigated: two activated charcoal products, a bentonite clay, two commer-cial mixed fining agents made of bentonite and charcoal, two yeast cell wall products, and a plant fiber-based novel filter additive. The results of this study show that all the agents tested reduced both residues and aromavolatile compounds in wine, with activated charcoal having the strongest effect and bentonite the weakest. The mixed agents and yeast wall products showed less aroma losses than charcoal products, but also lower residue reduction. Plant fibers showed good reduction of pesticides with moderate aroma damage, but these results need to be con-firmed under practical conditions.

The use of cation exchange resins for wine acidity adjustment: Optimization of the process and the effects on tartrate formation and oxidative stability

Acidity adjustments are key to microbial control, sensory quality and wine longevity. Acidification with cation exchange resins -in acid cycle- offers the possibility to reduce the pH by exchanging wine cations, such as potassium (K+), for hydrogen ions (H+). During the exchange process, the removal of potassium and calcium ions contributes to limiting the formation of tartrate salts, thus offering an alternative solution to conventional methods for tartrate stability. Moreover, the reduction of wine pH and the removal of metals catalyzers (e.g. iron) could positively impact the wine’s oxidative stability. Therefore, the aims of this work were (a) to optimize the ion exchange process by testing different volumes and concentrations of sulfuric acid (H2SO4) during the acid cycle, (b) evaluate the effects of the ion exchange process on the formation of tartrate salts, and (c) analyze the oxidative stability of the treated wines.

«Nektar» -the new red variety wine grape aromatic high quality

The multi-annual study of the International Genetic Bank of the Grape Vine has shown that red varieties are enough, but the red varieties that produce high-quality red wine are minimal.

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…

Contribution du potentiel glycosidique à l’arôme des vins de Grenache noir et Syrah en Vallée du Rhône

Grenache Noir and Syrah are the predominant grape varieties in the French Rhone valley vineyard, and produce wines with well differentiated aromatic notes. This study aimed at investigating the contribution of glycoconjugated precursors to these aromatic specificities, through their analytical profiles and the sensory influence of the odorant compounds they release during wine aging. The aglycones released by enzymatic hydrolysis of glycosidic extracts

ENRICHMENT OF THE OENOLOGICAL MALDI-TOF/MS PROTEIN SPECTRA DATABASE FOR RELIABLE OENOLOGICAL YEAST AND BACTERIA IDENTIFICATION

The Matrix Assisted Laser Desorption/Ionization–Time-Of-Flight Mass Spectrometry (MALDI-TOF MS) technology is commonly used in food and medical sector to identify yeast or bacteria species isolated from a nutritive culture media. Since a decade, brewery and oenology industries have been attracted to this method which combines fast analysis times, reliability and low cost of analysis. Briefly, this method is based on the comparison of the MALDI-TOF/MS protein spectra of an isolated colony of yeast or bacteria with those contain in a manufacturer’s reference protein spectra database. Initiated in 2015, the creation of the first oenological mass spectra database has proved to be essential for increase quality of species identification.

Water recharge before budbreak and/or deficit irrigation during summer: agronomic effects on cv. Tempranillo in the D.O. Ribera del Duero

The availability of water in the soil and the water status of the vineyard are proving to be determining factors for crop management in the current context of climatic variation

Soil electrical resistivity measurement: from terroir characterization to within-field crop inputs management

Soil Electrical Resistivity measurement is a zoning tool used by soil scientists and agronomists in viticulture. Indeed, the measure enables to optimize pedological surveys

Analysis of climate spatio-temporal variability in the Conegliano-Valdobbiadene DOCG wine district

Local climate characterization is fundamental in terroir description, yet global change perspectives raise questions about its feasibility, since temporal stability cannot be no more assumed for the forthcoming years.