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…

Effect of soil particle size on vine water status, leaf ABA content and berry quality in Nebbiolo grapes

The root and shoot abscisic acid (ABA) accumulation in response to water deficit and its relation with stomatal conductance is longtime known in grapevine. ABA-dependent and ABA-independent signalling response to osmotic stress coexist in sessile plants. In grapevine, the signaling role of ABA in response to water stress conditions and its influence on berry quality is critical to manage grapevine acclimation to climate change.

The impact of nutrition label formats on wine consumer preferences

Recent regulations concerning alcoholic beverages have prompted producers to revise their product labels to incorporate nutritional information. In this context, qr codes containing such information, known as e-labels, are now being employed on wine labels for the first time.

Accurate Quantification of Quality Compounds and Varietal Classification from Grape Extracts using the Absorbance-Transmittance Fluorescence Excitation Emission Matrix (A-TEEM) Method and Machine Learning

Rapid and accurate quantification of grape berry phenolics, anthocyanins and tannins, and identification of grape varieties are both important for effective quality control of harvesting and initial processing for wine making. Current reference technologies including High Performance Liquid Chromatography (HPLC) can be rate limiting and too complex and expensive for effective field operations

The weak role of organic mulches in shaping bacterial communities in grapevine

The interest in sustainable and ecologic agricultural practices in grapevine has grown significantly in recent years in the context of ecological transition. Organic mulches are treatments that support the circular economy and positively affect the soil and the plant. They are an alternative to herbicides and other conventional practices since they may influence soil moisture, erosion, structure and weed control. However, their effects on the soil and must microbiota remain unknown.

Climate change impact study based on grapevine phenology modelling

In this work we present a joint model of calculation the budbreak and full bloom starting dates which considers the heat sums and allows reliable estimations for five white wine grape varieties

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…

Three Nebbiolo clone anthocyanin profile as affected by environmental conditions

Vitis vinifera ‘Nebbiolo’ cultivar is a 3’-subsituted anthocyanin prevalent wine variety. It is grown in North-West Italy for the production of high quality ageing wines. In the present work berry skin anthocyanin amounts and profiles of the clones CVT 308, CVT 423 and CVT 142 were studied in 2004 and in 2005 in four environmentally different locations of North-West Italy: Donnas (steep mountain area), Monforte (hilly area, with a pH of 8.1), Vezza (hilly area, with a pH of 8.2) and Lessona (plain area, with a pH of 4.8).

Metal reducing agents (Fe and Al) as possible agents to measure the dimensions of the hydrogen sulfide (H2S) pool of precursors in wines

Reductive wine fault is characterized by the presence of odors such as rotten eggs or spoiled camembert cheese, originating from hydrogen sulfide (H2S) and methanethiol (MeSH) [1]. These compounds stabilize in polysulfide forms, creating a complex pool of precursors that will revert to both molecules when the environment becomes anoxic [2].

Enological potential of red grapes: cultivars and geographic origin of vineyards

The study of technologic and phenolic maturation is very efficient to determinate quality potential of red grapes cultivars and clones under different maturity levels or geographic origins

Enhancing vineyard resilience: evaluating sustainable practices in the Douro demarcated region

In mediterranean agriculture, sustainability and productivity are seriously threatened by climate change and water scarcity. This situation is exacerbated by poor management practices such as excessive use of agrochemicals, overgrazing, and monoculture. The Douro demarcated region (ddr) is an emblematic region, classified world heritage site by UNESCO in 2001. Viticulture is the main agricultural activity in DDR, widely known to produce port wine.

Investigation of cellulose nanofiber-based films used as a protective layer to reduce absorption of smoke phenols into wine grapes

Volatile phenols from wildfire smoke are absorbed by wine grapes, resulting in undesirable smoky and ashy sensory attributes in the affected wine.[1] Unfortunately the severity of wildfires is increasing, particularly when grapes are ripening on the vine. The unwanted flavors of the wine prompted a need for solutions to prevent the uptake of smoke compounds into wine grapes. Films using cellulose nanofibers as the coating forming matrix were developed as an innovative means to prevent smoke phenols from entering Pinot noir grapes. Different film formulations were tested by incorporating low methoxy pectin or chitosan.