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…

Gamma-ray spectrometry In Burgundy vineyard for high resolution soil mapping

Aim: A soil mapping methodology based on gamma-ray spectrometry and soil sampling has been applied for the first time in Burgundy. The purpose of this innovative high-resolution mapping is to delimit soil areas, to define elementary units of soil for terroir characterization and vineyard management. The added value of this integrated approach is a continuous geophysical mapping of the soil with an investigation depth of 60cm.

Cell-to-cell contact modulates Starmerella bacillaris early death in mixed fermentations with Saccharomyces cerevisiae in a couple-dependent way

AIM: The diversity and complexity of the fermentation ecosystem during wine making limits the successful prediction of wine characteristics. The use of selected starter cultures has allowed a better control of the fermentation process and the production of wines with established characteristics. Among them, the use of mixed fermentations with Starmerella bacillaris and Saccharomyces cerevisiae yeasts has gained attention in recent years due to the fructophylic nature of the first and the ability of this inoculation protocol to reduce the acetic acid and ethanol content of the wines.

Effect of multi-level and multi-scale spectral data source on vineyard state assessment

Currently, the main goal of agriculture is to promote the resilience of agricultural systems in a sustainable way through the improvement of use efficiency of farm resources, increasing crop yield and quality under climate change conditions. This last is expected to drastically modify plant growth, with possible negative effects, especially in arid and semi-arid regions of Europe on the viticultural sector. In this context, the monitoring of spatial behavior of grapevine during the growing season represents an opportunity to improve the plant management, winegrowers’ incomes, and to preserve the environmental health, but it has additional costs for the farmer. Nowadays, UAS equipped with a VIS-NIR multispectral camera (blue, green, red, red-edge, and NIR) represents a good and relatively cheap solution to assess plant status spatial information (by means of a limited set of spectral vegetation indices), representing important support in precision agriculture management during the growing season. While differences between UAS-based multispectral imagery and point-based spectroscopy are well discussed in the literature, their impact on plant status estimation by vegetation indices is not completely investigated in depth. The aim of this study was to assess the performance level of UAS-based multispectral (5 bands across 450-800nm spectral region with a spatial resolution of 5cm) imagery, reconstructed high-resolution satellite (Sentinel-2A) multispectral imagery (13 bands across 400-2500 nm with spatial resolution of <2 m) through Convolutional Neural Network (CNN) approach, and point-based field spectroscopy (collecting 600 wavelengths across 400-1000 nm spectral region with a surface footprint of 1-2 cm) in a plant status estimation application, and then, using Bayesian regularization artificial neural network for leaf chlorophyll content (LCC) and plant water status (LWP) prediction. The test site is a Greco vineyard of southern Italy, where detailed and precise records on soil and atmosphere systems, in-vivo plant monitoring of eco-physiological parameters have been conducted.

A new approach for sensory characterization of grape. Relationship with chemical composition

Characterize taste and mouthfeel properties of grapes elicited by the phenolic fraction (PF) of grape berries and establish relationships with chemical variables. METHODS: As many as 31 diverse grape lots of Tempranillo Tinto and Garnacha Tinta from three different regions were harvested. Grapes were destemmed and macerated in 15% of ethanol for one week and extracts were submitted to solid phase extraction. The recovered polyphenolic fraction was reconstituted in wine model and characterized by a panel of 21 wine experts employing a list of 23 taste and mouthfeel-related attributes following a rate-k-attributes methodology. RESULTS: Six significant attributes among the 31 samples differed based on ANOVA results: “dry”, “coarse”, “bitter”, “dry on tongue”, “sticky” and “watery”. PCA with VARIMAX algorithm was calculated.

Influenza del sito di coltivazione nella espressione aromatica del Moscato liquoroso di Pantelleria

ln 1997, twenty six cultivation sites of cv. Muscat of Alexandria different for pedological conditions, altitude and exposition were selected through ail Pantelleria isle. ln each site, described and classified according to USDA Soil Taxonony and FAO Soil Classification methods, grapes, collected at technological ripening, were microvinificated, following a standard procedure which allowed to obtain the naturally sweet wine DOC Moscato di Pantelleria. Wines, five months after vinification, were analysed by gaschromatography.

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…

Evapotranspiración de viñedo en secano y evaporación de barbecho en “La Mancha”

Un 94 % del viñedo español se cultiva con métodos y técnicas propias de los sistemas agrícolas desarrollados en secano en regiones de clima semiárido, donde las precipitaciones anuales raramente exceden los 500 mm

Méthode et outils de valorisation des terroirs en cave coopérative

Depuis le début des années 90, les vignerons des Caves Coopératives de l’Appellation “Côtes du Rhône” se sont penchés, au sein des structures de réflexion du Syndicat Général, sur deux axes de réflexion:
– Détermination des critères de sélection et de rémunération différenciée des apports de vendange;
– Organisation des sélections de vendanges sur la base des terroirs afin d’augmenter quantitativement le potentiel de sélection au sein de l’unité de production.

How much does the soil, climate and viticultural practices contribute to the variability of the terroir expression?

When considering the application of a systemic approach to assess the intrinsic complexity of agricultural production, the following question immediately arises

Harnessing biodiversity to improve grapevine rootstock adaptation to drought

Drought is one of the most challenging threats for viticulture because of its impact on reducing yield and on the composition of grapes.

Different soil types and relief influence the quality of Merlot grapes in a relatively small area in the Vipava Valley (Slovenia) in relation to the vine water status

Besides location and microclimatic conditions, soil plays an important role in the quality of grapes and wine. Soil properties influence…