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…

Étude de la composante climatique du terroir viticole en Val de Loire : relation avec les facteurs physiques du milieu

The research carried out by the URVV of the INRA center in Angers aims to develop a methodology for the integrated characterization of the natural factors of viticultural terroirs, representative of the operating conditions of the vine and the sensory differences of the wines. In this context, the concept of Basic Terroir Unit (UTB) has been developed. The UTB represents a viticultural surface of variable geographical extension, defined as the association in a given place of a geological, pedological and landscape component, Morlat (1989), Riou et al. (1995).

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.

Exploring the genetic diversity of leaf flavonoids content in a set of Iberian grapevine cultivars: preliminary results

The use of grapevine genetic diversity is a way to mitigate the negative impacts of climate change on viticulture systems. Leaf epidermal flavonoids (including flavonols and anthocyanins) are involved in plant defense mechanisms against environmental stresses, like high temperatures or excessive solar radiation [1,2]. Among other factors, they modulate light absorption, which reduces photoinhibition processes in photosynthetic tissues [1]. Therefore, the identification of grapevine cultivars with an increased content on leaf epidermal flavonoids arises as a potential avenue to improve grapevine tolerance to some detrimental environmental stresses.

Metabolomics comparison of non-Saccharomyces yeasts in Sauvignon blanc and Shiraz

Saccharomyces cerevisiae (SC) is the main driver of alcoholic fermentation however, in wine, non-Saccharomyces species can have a powerful effect on aroma and flavor formation. This study aimed to compare untargeted volatile compound profiles from SPME-GC×GC-TOF-MS of Sauvignon blanc and Shiraz wine inoculated with six different non-Saccharomyces yeasts followed by SC. Torulaspora delbrueckii (TD), Lachancea thermotolerans (LT), Pichia kluyveri (PK) and Metschnikowia pulcherrima (MP) were commercial starter strains, while Candida zemplinina (CZ) and Kazachstania aerobia (KA), were isolated from wine grape environments. Each fermentation produced a distinct chemical profile that was unique for both grape musts. The SC-monoculture and CZ-SC sequential fermentations were the most distinctly different in the Sauvignon blanc while the LT-SC sequential fermentations were the most different from the control in the Shiraz fermentations.

THE EFFECT OF BENTONITE FINING ON THE VOLATILE AND NON-VOLATILE PROFILE OF ITALIAN WHITE WINES

Marselan wines have an unusual high proportion of seed derived tannins from grapes having high proportions of skins, which are rich in tannins. But the causes behind this characteristic have not yet been identified. In vintage 2023 wines were made at experimental scale (9 kg by experimental unit) from Arinarnoa, Marselan and Tannat Vitis vinifera grape cultivars by traditional maceration, and by techniques aimed to increase the wine content in skin derived tannin: addition of extraction enzymes, addition at vatting of grape-skin enological tannins, or by extended maceration, known to increase the seed derived tannin contents of wines. Macerations were of 7 days, except in the extended macerations that were of 15 days.

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…

Grapevine genotypes with potential for reducing the carbon footprint in the atmosphere and cultivation in a biological system

The concentration of CO2 in the atmosphere is increasing from year to year. Taking into account the calculations of the greenhouse gas inventory, it was found that approximately 70% of CO2 in the atmosphere is absorbed by vegetation (forests, agricultural land, etc.).

AROMATIC AND FERMENTATIVE PERFORMANCES OF HANSENIASPORA VINEAE IN DIFFERENT SEQUENTIAL INOCULATION PROTOCOLS WITH SACCHAROMYCES CEREVISIAE FOR WHITE WINEMAKING

Hanseniaspora vineae (Hv) is a fermenting non-Saccharomyces yeast that compared to Saccharomyces cerevisiae (Sc) present some peculiar features on its metabolism that make it attractive for its use in wine production. Among them, it has been reported a faster yeast lysis and release of polysaccharides, as well as increased ß-glucosidase activity. Hv also produces distinctive aroma compounds, including elevated levels of fermentative compounds such as ß-phenylethyl acetate and norisoprenoids like safranal. However, it is known for its high nutritional requirements, resulting in prolonged and sluggish fermentations, even when complemented with Sc strain and nutrients.

Interaction among grapevine cultivars (Sangiovese, Cabernet-Sauvignon and Merlot) and site of cultivation in Bolgheri (Tuscany)

Different “landscape unit” 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 the 1992-1993 period. In all cultivar (Sangiovese, Cabernet Sauvignon and Merlot) x landscape unit combinations, experimental plots were chosen in homogeneous vineyards, single cordon trained (about 3300-4500 vines/hectare). Grape maturation was studied by weekly samples of berries from veraison to vintage in the 1992-1995 period. At harvest yield and must composition traits were measured and, from the most représentative plots, sixty kilograms of grapes were harvested each year and vinified according to a standardised scheme. Wines were evaluated by standard chemical and sensory analyses.

Tracing glycosidically-bound smoke taint markers from grape to wine

The increasing frequency of wildfires on the West Coast of the USA is seen as a significant risk for the grape and wine industry. Research has shown that perceived smoke impact in wines correlates with increases in volatile phenols (VPs) in grapes exposed to fresh smoke.

Identification of green, aggressive and hard character of wines by a chemo-sensory directed methodology

With climate change, it is progressively more often to obtain grapes with an acceptable content in sugars or acids but with immature tannins described as green, aggressive or hard (noted as GAH onwards). During winemaking, the oenologist has to make decisions related to the elaboration of such grapes based mainly on empirical experience, given the lack of objective criteria to this concern. An increase in the chemical and sensory knowledge of immature tannins would allow managing this GAH character of grapes with the maximum possible efficiency during winemaking processes. The present work aims at isolating and identifying the group of compounds responsible for the GAH character present in wines.