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…

Influence of the irrigation period in Tempranillo grapevine, under the edaphoclimatic conditions of the Duero river valley

Irrigation of vineyards is a matter of controversial arguments at areas of high quality wine production. Besides, the effects of the water in the plant are closer related to the water availability than to the irrigation regime.

Do high temperature extremes impact berry tannin composition?

Flavonoids, including flavonols, anthocyanins, and tannins, are
important contributors to grape and wine quality, and their biosynthesis is strongly influenced by bunch microclimate. While the synergistic effect of light and temperature has been intensively examined on flavonoids in relation to bunch exposure, studies targeting the sole effect of high temperature have mostly
focused on anthocyanins during the ripening period. With tannin biosynthesis starting around flowering, heatwaves occurring earlier in the grape growing season could be critical. Only a few papers report the impact of temperature on tannin synthesis and accumulation; to date, none have examined the effect of high temperature extremes which, in the context of climate change, relates to increases in heatwave intensity.

New insights of translocation of smoke-related volatile phenols in vivo grapevines

The increasing frequency of wildfires in grape-growing regions is seen as a significant risk for the grape and wine industry.

Decoupling the effects of water and heat stress on Sauvignon blanc berries

Climate changes have important consequences in viticulture, heat waves accompanied by periods of drought are encountered more and more frequently. This study aims to evaluate the single and combined effect of water deficit and high temperatures on the thiol precursors biosynthesis in Sauvignon blanc grapes. For this purpose, a protocol has been developed for the cultivation of berries on a solid substrate. The berries, collected at three different times starting from veraison and grown in vitro, were subjected to 4 different treatments: control (C), water stress (WS), heat stress (HS), combined water and heat stress (WSHS). Water stress was simulated by adding abscisic acid to the culture medium, while different temperatures, respectively 25°C and 35°C, were managed with two illuminated climatic chambers.

Producer organisations at the service of the favourable chain of values to winegrowers and winemakers: the example of France

French law and European Union law recognise the existence of interprofessional organisations that bring together all the links in the wine industry.

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…

Agronomic and oenological characterization of the intraspecific cross ‘Passau’ in the aim of its commercial use

The study of new wine grape cultivars can be interesting to diversify the local wine productions without using international varieties. With this aim some Vitis vinifera intraspecific crosses obtained by Prof. Dalmasso in the 1930s and registered in the Italian National Catalogue in 1977, have been studied in the last years.

Characterization of winegrape berries’ composition on sorting tables using hyperspectral imaging and AI

Comprehensive evaluation of grape composition at winery receiving areas often requires multiple measurements to ensure representativeness, as well as the use of analytical techniques that are time-consuming and involve sample preparation.

EVALUATION OF THE OENOLOGICAL POTENTIAL OF NEW RESISTANT VARIETIES MEETING TYPICAL BORDEAUX CHARACTERISTICS

Varietal innovation is a major lever for meeting the challenges of the agro-ecological transition of vi-neyards and their adaptation to climate change. To date, selection work has already begun in the Bordeaux region through the Newvine project. The aim of this project is to create new vine varieties with resistance to mildew and powdery mildew, adapted to the climatic conditions of the Bordeaux region and enabling the production of wines that are in line with consumer tastes and the expected typicity of Bordeaux wines.

Measures to promote biodiversity in viticulture—how do socio-economic factors influence implementation?

Context and purpose. In Germany, vineyards are typically intensively managed monocultural systems shaped by low structural variability.

From local classification to regional zoning. The use of a geographic information system (GIS) in Franconia / Germany. Part 3: classification of soil parameters in vineyards

La conservation de la fertilité du sol est un aspect primordial dans la viticulture durable. Différents paramètres, comme par exemple la topographie, la composition du sol, les conditions climatiques, influencent la fertilité du sol des surfaces viticoes.