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…

Adaptation of Lactobacilli towards low ph and SO2 to develop MLF in base musts for sparkling wines

In some white wines, malolactic fermentation (MLF) is very interesting, and for low pH wines this process is particularly difficult. Although MLF is generally not recommended for sparkling white wine, some winemakers prefer to promote MLF to contribute to organoleptic complexity. Oenococcus oeni is generally the bacterium of choice for MLF.

Improving the phenolic composition of cv tempranillo wines by blending grapes of different ripening state

The aim of this work was to reduce the alcohol content of Tempranillo wine. Tempranillo wines were produced by grapes harvested at different ripening dates (August 11 which was 21 oBrix and September 28 with 25 oBrix). At the second date, the Tempranillo wines were elaborated as follows: grapes were destemmed, crushed and collected into 50 L stainless-steel vats. Before preferementative maceration in cold, 50 % (M1) and 70 % (M2) of the must have been replaced by the same percentage of must from the first harvest. In addition, a control wine (C) was performed with only grapes from the second harvest.

Contrast of unfair trade practices in business-to-business relationships in the agricultural and food supply chain: An overview from the vitivinicultural perspective

According to the Directive EU 2019/633, European Union settled a minimum harmonised framework of rules to ensure the prohibitions of unfair commercial practices in business to business relationship of agrifood sector.

Assessing the impact of defoliation on grape volatiles profile and wine odor characteristics in four Greek red varieties (Vitis vinifera L.) using multivariate chemometrics

Context and purpose of the study. Cultivation techniques are widely recognized for their significant impact on the aroma profile of grapes and wines.

Veraison as determinant for wine quality and its potential for climate adapted breeding

The evaluation of new grapevine genotypes regarding their potential to produce high quality wines is the time limiting factor in the process of grapevine breeding. Hence, the development of quality-related markers useable in marker-assisted selection (MAS) as well as in prediction models for this bottleneck trait will tremendously enhance breeding efficiency. In extensive studies a training set of a segregating white wine F1 population (150 F1 genotypes = POP150; `Calardis Musqué´ x `Villard Blanc´) was deeply phenotyped and genotyped for model development and QTL analysis.

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 large-scale study of thiol precursor distribution in red grape berry compartments and implications for thiol-type red wine production

Climate change and the growing need to reduce the use of phytosanitary products demand the exploration of disease-resistant grape varieties and/or adapted to drought conditions.

Descriptive analysis of Sangiovese and Cabernet-Sauvignon wines from different terroirs in D.O.C. Bolgheri (Tuscany)

Different terroirs have been identified in Bolgheri area (a viticultural appellation in the Tirrenian coast of Tuscany) by the aid of pedological, landscape and agronomic observations in 1993. Numerous preliminary observations suggested that wines obtained from these different terroirs were unique.

Vineyard soils and landscapes of the Burgundy Côte (France): a historical construction worth preserving

The construction of vineyard landscapes along the Burgundy Côte is the result of geological processes and of human labour. Substratum diversity in this vineyard is the result of a very long history explained by the diversity of Jurassic sedimentary facies and Tertiary tectonic activity. The nature and thickness of Quaternary deposits (Weichselian scree debris and alluvial fans) reflect sediment dynamics concurrent with the last glaciation.

Coming of age: do old vines actually produce berries with higher enological potential than young vines? A case study on the Riesling cultivar

Consumers and the wine industry tend to agree on the ability of old vines to produce fruit that allows the production of wine of superior character. However, despite past and ongoing research, objective evidence of this point of view is still debated and studies on robust, specifically dedicated plots are scarce. Thus the impact of grapevine age on berry oenological potential and wine quality remains an open question. To try to objectively address the issue, a unique vineyard was established at Geisenheim University, Germany. It was planted in 1971 with cv. Riesling grafted on 5C Teleki. In 1995 and 2012, several rows were uprooted and replanted with the same rootstock/scion combination, resulting in a vineyard with alternate rows of identical plant material, but with different planting dates. The parameters of technical maturity and grape composition at harvest were analyzed during seasons 2014, 2015, 2016 and 2017 combining HPLC and enzymatic methods. Separate micro-vinifications were made for each age group and wine composition was analyzed by a combination of 1H-NMR and SPE-GC-MS.

High-throughput direct monitoring of microbial resources for oenology by direct injection mass spectrometry

Microorganisms have been widely used in oenology since prehistoric times. Their metabolism significantly impacts many wine properties and is particularly essential for the production of flavor compounds, thereby affecting perceived wine quality.