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…

The influence of site aspect and pruning types on Pinot Noir phenology and shoot growth

Aim: Managing the influence that terroir in vineyards has on vine development depends on improving our understanding the effect of the interaction of within-site variability, within-vine variability, and management practices (such as pruning types) on phenology and vine development. This study evaluates the consequence of site aspect

Petrolomics-derived data interpretation to study acetaldehyde-epicatechin condensation reactions

During red wine ageing or conservation, color and taste change and astringency tends to reduce. These changes result from reactions of flavan-3-ols and/or anthocyanins among which condensation reactions with acetaldehyde are particularly important. The full characterization of these reactions has not been fully achieved because of difficulties in extracting and separating the newly formed compounds directly from wine. Model solutions mimicking food products constitute a simplified medium for their exploration, allowing the detection of the newly formed compounds, their isolation, and their structure elucidation.

Ultra-High Pressure Homogenization (UHPH): a technique that allows the reduction of SO2 in winemaking

Ultra-High Pressure Homogenization (UHPH) is an innovative, efficient and non-thermal technology that can be applied at different stages in winemaking in order to reduce or avoid the use of sulphites. During 2022 vintage, a batch of Xarel·lo must was processed by UHPH at 300 MPa with an inlet temperature (Ti) of 4 ºC. In order to verify the influence of the UHPH treatment in wine characteristics, alcoholic fermentations with this must (UHPH) were carried out and compared with a control batch (without SO2 addition (C)) and a sulphited batch, in which 60 mg/L of total SO2 (SO2) were added.

Impact of the maturity and the duration of maceration on phenolic composition and sensorial quality of Divico wines

Following its approval in 2013 by Agroscope, Divico became the first interspecific grape variety in Switzerland with high resistance to downy mildew (Plasmopara viticola) and grey rot (Botrytis cinerea), and medium resistance to powdery mildew (Uncinula nectator). Extremely riche in color, Divico grapes showed great enological potential to different styles of wine. Quickly, many wine growers were interested in planting this promising variety. Many of its potential are to be explored in the coming years.

Reduced berry skin epi-cuticular wax and cutin accumulation associates with a genomic deletion and increased polyphenols extractability in a clone of Tempranillo Tinto 

Tempranillo Tinto (TT) is the third-most planted red wine variety in the world, and it is mostly grown in the Iberian Peninsula. Spontaneous somatic variation appearing during vegetative propagation can be exploited to improve elite varieties as Tempranillo Tinto, including the selection of new phenotypes enhancing berry quality. We described previously that a somatic variant of TT with darker fruit color, the clone VN21, exhibits increased extractability of polyphenols during the winemaking process. To unravel the molecular mechanism underlying this phenomenon, we performed whole-genome resequencing to compare VN21 to other TT clones, revealing a 10 Mb deletion in chromosome 11 that likely affected only the L1 meristem cell layer of VN21 and tissues derived from it, such as external cell layers of berry skin.

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…

Untangling belowground response of grapevines to cover crop competition

Cover crops are planted in vineyards for multiple benefits including soil conservation, weed management, regulation of grapevine vegetative growth

Wine tourism in southern Italy: A surge in popularity and economic impact

Wine tourism has transformed from a leisure activity into a crucial part of the tourist experience, significantly contributing to rural tourism’s expansion in italy. It has witnessed a notable surge in popularity in recent years, evolving as a key motivator for travel (antonioli corigliano, 2002; brunori & rossi, 2000; città del vino & censis servizi, 2011; garibaldi, 2018; 2019a; 2020; montanari, 2009; romano & natilli, 2009). The allure of wine tourism, driven by sensory experiences and cultural immersion, continues to attract a diverse group of tourists. The economic impact is substantial, with events and festivals contributing approximately €2.5 billion annually.

Determination of the maturity status of white grape berries (Vitis vinifera L. cv Chenin) through physical measurements

La véraison, stade intermédiaire du développement de la baie de raisin, correspond au début de la maturation. Aux modifications de coloration de la pellicule sont associées une perte de fermeté, une diminution de l’acidité et une augmentation des teneurs en sucres et pigments ainsi que du volume de la baie. Le stade de véraison des cépages blancs reste difficile à apprécier visuellement. Son évaluation par palpation est subjective et donc sujette à caution.

Monitoring water deficit in vineyards by means of Red and Infrared measurements

Vineyard water availability is one of the most important variables both in plant’s production and wine quality, once it regulates several processes, among which the stomata activity. To avoid water deficit, wine producers introduced artificial irrigation in their vineyard, using a semi-empirical process to calculate water amount.

Adsorption of tetraconazole by organic residues and vineyard organically-amended soils 

Spain is the country with the largest wine-producing area in the EU and its productivity is largely controlled applying fungicides. However, residues of these compounds can move and contaminate surface and groundwater. The objective of this work was to evaluate the capacity of bioadsorbents from different origin to adsorb and immobilize tetraconazole by themselves or when applied as organic soil amendment, and to prevent soil and water contamination by this fungicide. The adsorption of tetraconazole by 3 organic residues: spent mushroom substrate (SMS), green compost (GC) and vine pruning sawdust (VP), as well as by vineyard soils unamended and amended individually with these residues at 1.5% (w/w) was evaluated using the batch equilibrium technique.