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…

Bioprotection en phase pré-fermentaire, synthèse de 3 ans d’expérimentations dans différentes régions viticoles

With growing consumer interest in products without chemical additives, limiting the use of sulfites is a priority for the wine industry. Bioprotection is a biological alternative that avoids or reduces the risks of alterations that have a negative impact on the organoleptic quality of wines and, ultimately, on their acceptability to consumers. bioprotection can also provide a response to the risks of microbiological deviations, which are increased both by climate change and by the organization of harvesting operations, which increasingly include the use of multi-bins filled at the vine, exposing the harvest to sometimes high temperatures for longer periods of time.

NACs intra-family hierarchical transcriptional regulatory network orchestrating grape berry ripening

Considering that global warming is changing berry ripening timing and progression, uncovering the molecular mechanisms and identifying key regulators governing berry ripening could provide important tools in maintaining high quality grapes and wine. NAC (NAM/ATAF/CUC) transcription factors represent an interesting family due to their key role in the developmental processes control, such as fruit-ripening-associated genes expression, and in the regulation of multiple stress responses. Between the 74 NAC family members, we selected 12 of them as putative regulators of berry ripening: NAC01, NAC03, NAC05, NAC11, NAC13, NAC17, NAC18, NAC26, NAC33, NAC37, NAC60 and NAC61.

Delimitation of Saint-Bris AOC: example of reasonning delimitation criteria from production customs

La définition de l’Appellation d’Origine précise que les caractères du produit doivent être dus au milieu géographique, celui-ci intégrant des facteurs naturels et humains.

Influence of the vintage, clone and rootstock on the chemical characteristics of Syrah tropical wines from Brazil

In the Northeast of Brazil, vines can produce twice a year, because annual average temperature is 26ºC, with high solar radiation and water availability for irrigation.

Zonazione aziendale nel territorio del Chianti classico e valorizzazione dei vini

Nell’ambiente del Chianti Classico è stato applicato un progetto di zonazione aziendale con l’objettivo di valorizzare le produzioni dei diversi vigneti. In particolare sono stati individuati sette siti, sottoposti a studio particolareggiato per un triennio.

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…

Transition metals and light-dependent reactions: application of a response surface methodology approach

Light-induced reactions can be responsible for detrimental changes of white and rosé wines. This is associated to the photo-degradation of riboflavin (RF) and of methionine (Met) causing the appearance of light-struck taste (LST).

Melatonin priming retards fungal decay in postharvest table grapes 

Postharvest losses of fruits may reach in some cases 40% in developed countries. This food waste has a significant carbon footprint and makes a major contribution toward greenhouse gas emissions so sustainable postharvest strategies are being investigated.
Melatonin, a well-known mammalian neurohormone, has been investigated as a priming agent to slow down fungal decay progression in postharvest climacteric and some non-climacteric fruits. However, the molecular and metabolic mechanisms responsible for such enhancement of disease tolerance are largely unknown.

Modeling sugar accumulation dynamics of a wide variety of grape cultivars (Vitis vinifera L.)

Climate change is a major challenge in wine production. The IPCC (2014) projected that by the end of the 21st century average temperatures will increase by 1-3.7°C. Consequently, harvest dates could advance by approximately 30 days. A general observed trend is the increase in berry sugar content and decrease in organic acids, posing challenges for winegrowers. Variability among cultivars is a precious resource to adapt viticulture to a changing environment.

Towards a unified terroir zoning methodology in viticulture

In viticulture, terroir is a key concept that refers to an area and thus possesses a geographical dimension. Hence, zoning of viticultural terroir is an important issue

The grapevine QTLome is ripe: QTL survey, databasing, and first applications

Overarching surveys of QTL (Quantitative Trait Loci) studies in both model plants and staple crops have facilitated the access to information and boosted the impact of existing data on plant improvement activities. Today, the grapevine community is ready to take up the challenge of making the wealth of QTL information F.A.I.R.. To ensure that all valuable published data can be used more effectively, the myriad of identified QTLs have to be captured, standardised and stored in a dedicated public database.
As an outcome of the GRAPEDIA initiative, QTL-dedicated experts from around the world have gathered to compile the grapevine QTLome: the complete information (e.g., map positions, associated phenotypes) describing all experimentally supported QTLs for a specific trait.