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…

Can grapevine intra-varietal genetic variability be a tool for climate change adaptation? A case study at a hot and dry environment

Climate change projections point to an increase of temperatures and changes in rainfall patterns in the mediterranean region.

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.

Occurrence of methyl salicylate in lugana wines: aroma impact and biogenesis 

AIM Methyl salicylate (MeSA) has been reported as a potentially impactful compound in Verdicchio wines produced in central Italy. Lugana is another white wine produced in the north-east of Italy from a grape locally known as Trebbiano di Soave, sharing a very similar genetic background with Verdicchio. The aims of this study were evaluating MeSA occurrence in Lugana, assessing its aroma impact on white wines aroma and elucidating its biogenesis during vinification. METHODS Fifteen Lugana wines were analysed for methyl salycilate content in comparison with Verdicchio, Pinot grigio and Garganega wines. MeSA impact on white wine aroma was studied by means of triangular test, adding MeSA at different concentrations. Possible routes of MeSA formation by yeast were investigated by means of a high throughput assay in which S. cerevisiae cells were put in contact with precursor such as salicylic acid (esterification) or glycosidic extracts (glycosidase). Sub-fractions of Lugana glycosidic extracts were also obtained by HPLC fractionation, allowing further evaluation of precursors role.

Investigation on Valbelluna area and its oenological potentiality: case study on Prosecco DOC

Valbelluna valley is an area located in the northeastern Italy. It is extended from the East-West between Feltre and Belluno, along the Piave waterway and enclosed between Cansiglio valley on the South and the Dolomites in the North. Here, the villages of Limana and Trichiana are present, which are considered for decades potentially interesting areas to aim a niche production with own particular properties.The position of this area, its sun exposition, its soil composition and the microclimate, are ideal factors to obtain vines and consequently wines with unique features especially regarding the diversity and complexity aroma.

Climate change – variety change?

In Franconia, the northern part of Bavaria in Germany, climate change, visible in earlier bud break, advanced flowering and earlier grape maturity, leads to a decrease of traditionally cultivated early ripening aromatic white wine varieties as Mueller-Thurgau (30 % of the wine growing area) and Bacchus (12 %). With the predicted rise of temperature in all European wine regions the conditions for white wine grape varieties will decline and the grapes themselves will lose a part of their aromatic and fruity expression. Variety change towards the cultivation of later ripening white wine varieties is a very expensive and long-term process, and must be accompanied by special marketing efforts.

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…

Exploring multisensory interactions through the study of astringency diversity of mono-varietal Italian red wines

According to the OIV Focus 2017 estimating the vine varieties distribution in the world, Italy is the richest grape producing country in terms of varieties.

Effects of the addition of biochar on the chemical parameters of a vineyard soil in South Tirol, Italy

[lwp_divi_breadcrumbs home_text="IVES" use_before_icon="on" before_icon="||divi||400" module_id="publication-ariane" _builder_version="4.20.4" _module_preset="default" module_text_align="center" module_font_size="16px" text_orientation="center"...

Viticultural zoning using spatial analysis: characterizing terroirs over the Southern part of the Côtes-du-Rhône appellation (France)

Les approches du terroir en tant qu’entité géographique (zonages) connaissent un développement accru récent en lien avec l’essor des SIG. Les méthodes, les objectifs et les critères utilisés varient considérablement selon les études.

Wine metabolomics and sensory profile in relation to terroir: A case study focusing on different wine-growing areas of Piacenza Province (Italy)

Aim: In this work, we have optimized a robust methodology for investigating possible correlations between the phytochemical profile of wine and the terroir (including the climate), considering the specific wine-growing area. In particular, the untargeted metabolomic and sensorial profiles of Gutturnio DOC commercial wines (both still and “frizzante” types) from different production areas in the Piacenza province were determined. The geographical areas taken into consideration for this study consisted in Val Tidone, Val Nure and Val d’Arda.

Ampelograpic and genetic characterisation of grapevine genetic resources from Ozalj-Vivodina region (Croatia)

Ozalj- vivodina region is small vine growing area (only about 100 hectares of vineyards), but with significant number of old, ancient vineyards planted between 50 and 100 years ago. Trend of abandoning or replanting ancient vineyards takes place for the last 30 years. This trend results in grapevine germplasm erosion because traditional varieties are replaced with well known international varieties.Few known traditional varieties are dominantly present in ancient vineyards together with many others of unknown identity. Historical data about prevalence and characteristic of varieties on this area are very poor.