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 methyl jasmonate foliar application to vineyard on grape volatile composition over three consecutive vintages

An alternative to improve grape quality is the application to the vineyard of elicitors. Although these compounds were first used to increase resistance of plants against pathogens, it has been found that they are also able to induce mechanisms involved in the synthesis of phenolic compounds and some amino acids. However, researches about the influence of elicitors on grape volatile composition are scarcely. Therefore, the aim of this work was to study the influence of methyl jasmonate (MeJ) foliar application on grape aroma composition over three consecutive vintages. MeJ was applied to Tempranillo grapevines at a concentration of 10 mM in 2013, 2014, and 2015 years. Control plants were sprayed with water.

The opportunities offered by the climate change

Based on the results of experiments since 2000 at the Institut Agro Montpellier and at INRAE – Pech Rouge, and on the international experience acquired during scientific missions, a global reflection on the opportunities offered by climate change is proposed.

Comparison of plant nutrients in the soil solution and bleeding sap of grapevine cvs

In this study macro and micro nutrients of plants (N = NH4 + NO3 , P, K, Ca, Na, Zn, Mn, Fe and Cu) were determined both in soil solution and bleeding sap and compared each other. Bleeding sap was collected from the nine varieties of grapevine Cvs. grafted on 5BB rootstock and grown in different soil conditions. For all varieties, plant nutrients content in bleeding sap as higher than in soil solution except for Ca and Na. While in soil solution Ca content was found at 10209 ppm, this value in bleeding sap was 49.20 ppm (Kozak Beyazy), 55.38 ppm (Trakya Ylkeren), 50.37 (Cardinal) and 74.27 ppm (Tekirdaô Çekirdeksizi) respectively. For the same varieties the Na values were as follows : 7.16 ppm (in soil solution) : 4.8, 3.23, 4.21,4.58 ppm (in bleeding sap) respectively. K content in bleeding sap was higher than in soil solution for a few varieties, and lower in some varieties. Traces of Fe and Cu were found in both media.

Contribution of viticultural and oenological factors to the aromatic potential of white Colombard wines from the south west of France Gascony vineyard

The aim of this work is to determine the influence of viticultural and oenological factors to the aromatic potential of white wines from Colombard variety in the south west of France Gascony vineyard.

Spatial suitability analysis for site selection of vineyards using biophysical models and computational intelligence

Developing a sustainable agricultural production system and acquiring the full potential of land resources requires employing land-use assessment. This entails knowledge of the climate, soil, and topography of the area of interest.

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…

First application of an original methodology created to overcome conflicts between stakeholders in an important wine-growing territory: methodology, results, and perspectives in the application of sustainability EME4.1C

Considering the previous research and activities, also, on Sustainability EME4.1C which, as widely known, considers in a harmonious chain all the factors material, immaterial, moral and spiritual related to all aspects environmental, economic, social, existential, relational, ethical, technical and “MetaEthic” indexed 4.1C

Rootstock regulation of scion phenotypes: the relationship between rootstock parentage and petiole mineral concentration

Rootstocks not only provide tolerance to Phylloxera, but also ensure the supply of water and mineral nutrients to the whole plant. Rootstocks are an important way of adapting to environmental conditions while conserving the typical features of scion varieties. We can exploit the large diversity of rootstocks used worldwide to aid this adaptation. The aim of this study was to characterise rootstock regulation of scion mineral status and its relation with scion development.

Estimation of stomatal conductance and chlorophyll fluorescence in Croatian grapevine germplasm under water deficit    

Water deficit profoundly impacts the quality of grapes and results in considerable reductions in crop yield. First symptoms manifest with reduced stomatal conductance and transpiration, accompanied by the wilting of apical leaves and tendrils. So far, there is no available data on the water stress response in Croatian grapevine germplasm. Therefore, objective of this study was to determine influence of genotype and treatment on stomatal conductance (gsw), transpiration (E), electron transport rate (ETR), and quantum efficiency in light (PhiPS2).

Analysis of the oenological potentials of different oak forests in Hungary

Like France, Hungary has many oak forests used for making barrels since many years. But if the differences between the woods of the North, the East and the South-West forests of France are well known, this is probably not the case of Hungarian forests. However taking into account the essential differences of climates and soils, differences must be significant and the general name “Hungarian oak” must not have any real meaning. We have studied precisely (determination of concentrations of volatile and non-volatile wood compounds, anatomical criteria, measurement of antioxidant capacity) of oaks collected from northeastern Hungary and others collected from the Danube valley in the northwest of the country.

Consumo hídrico de la vid, c.v. Listán negro, en la comarca de Tacoronte-Acentejo. Tenerife

Durante el bienio 1998-1999 se estudió el uso consuntivo de cultivos de viña var. Listán negro, en cuatro fincas situadas en la Comarca de Tacoronte-Acentejo, en la isla de Tenerife.