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…

Overcoming habit formation in the production of wine

Evidence indicates that climate change affects the environment, human health, and well-being via drought, increasing greenhouse effect, and climatic catastrophes. As the wine sector is also negatively affected by climate change, the role of climate change mitigation and adaptation policies is important in wine production. One example of an adaptation policy is the implementation of grapevine genetics (duchene, 2016), while organic farming may be used as an approach to mitigate the consequences of climate change (vinci et al., 2022). To this end, the european commission’s objective is to reach the european green deal target of at least 25% of the european union’s agricultural land under organic farming by 2030.

Algae protein: fining agent for white wine, sustainable, non-allergenic and animal-free

The development of non-animal and non-allergenic alternatives to traditional protein fining agents used in winemaking is of critical importance in order to ensure consumer safety and production sustainability. This study evaluates the effect of protein extracted from three types of algae (spirulina, chlorella vulgaris and tetraselmis chuii) as fining agents on the polymeric proanthocyanidin content responsible for astringency, as well as their effect on the colour, phenolic composition and volatile aroma of two white wines (a and b).

Effects of Non-Grape Materials (MOG) on wine quercetin composition: insights from synthetic and Merlot grape juice fermentation

Quercetin precipitation has become an increasingly common issue in red wine, often resulting in visually unpleasant sediments and diminished product quality.

Consequences of apical leaf removal on grapevine water status, heat damage, yield and grape ripening on Pinot n and Chardonnay

Climate change presents a significant challenge to grape growing worldwide as increased temperatures lead to wines with increased sugar and pH levels. Manipulation of the exposed leaf area is a powerful lever governing the assimilation and storage of non-structural carbohydrates in grapevines. Reducing the leaf-to-fruit ratio is now considered as a tool for adapting to hotter and dryer grape growing conditions.

Extraction-modelling approach demonstrates grapevine rooting patterns varies significantly as a result of contrasting ground management and growing environment in cover cropped vineyards

The use of cover crops in viticulture has increased in recent decades as growers seek to reduce herbicide use, improve soil organic matter and biodiversity, and minimize soil-related agronomic issues such as compaction and erosion.

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…

Berry shrivel causes – summarizing current hypotheses

Diverse ripening disorders affect grapevine resulting in high economic losses worldwide. The common obvious symptom is shriveling berries, however the shriveling pattern and the consequences for berry quality traits are distinct in each disorder. Among them, the disorder berry shrivel is characterized by a reduced sugar accumulation short after the onset of berry ripening leaving the clusters unsuitable for wine processing. Although our knowledge on BS increased recently, potential internal or external triggers contributing to the induction of BS are yet to be explored.

Possible Reduction Method Of Volatile Acid Content And Polyphenols Of Tokaj Aszú Wines With The Aid Of Citosan Bactericid Wine-Treatments

The historical Tokaj region in northeast Hungary is a UNESCO World Heritage region since 2002 owning 5.500 ha vineyards. Produced from „noble rot” grapes, Tokaji Aszú is known as one of the oldest botrytized wines all over the world. Special microclimatic conditions (due to Bodrog and Tisza rivers, Indian summer), soil circumstances (clay, loess on volcanic bedrock) and grape-varieties (Furmint, Hárslevelű) of Tokaj-region offer favourable parameters to the formation of noble rot caused by Botrytis cinerea. The special metabolic activity of Botrytis results in noble rot grapes called “aszú” berries. The grapes undergo complex chemical modifications as the joint result of the enzymatic activity of Botrytis and the physical process of concentration.

Saccharomyces cerevisiae intraspecies differentiation by metabolomic signature and sensory patterns in wine

AIM: The composition and quality of wine are directly linked to microorganisms involved in the alcoholic fermentation. Several studies have been conducted on the impact of Saccharomyces cerevisiae on volatile compounds composition after fermentation. However, if different studies have dealt with combined sensory and volatiles analyses, few works have compared so far the impact of distinct yeast strains on the global metabolome of the wine.

The impact of decadal cold waves over Europe on future viticultural practices

A crucial issue associated with the long-term impact of climate change in viticulture concerns the capacity of resilience of the typical varieties currently cultivated in traditional areas. Indeed, regions that are currently characterized by optimal climatic conditions can cease to be so in the future. At the same time, new premium wine production regions may arise north of 50oN. Both these threats and opportunities are based on the assessment of a very likely gradual temperature increase along the 21st century, resulting from the ensemble mean of the state-of-the-art climate projections. Such an assessment is orienting decision-makers and stakeholders to rethink the grapevine cultivation zoning, prefiguring, for each variety, a shift at higher latitudes and/or at higher altitudes areas.

Effect of non-wine Saccharomyces yeasts and bottle ageing on the release and generation of aromas in semi-synthetic Tempranillo wines

Explore the variability and contribution of non-wine Saccharomyces yeasts and bottle aging on the release and generation of aromas of semi-synthetic Tempranillo wines, together with an in-depth study of the capacity of these strains to provide good fermentative and oenological qualities