Absorbance-transmission and fluorescence excitation-emission matrix (A-TEEM) with multi-block data analysis and machine learning for accurate intraregional classification of Barossa Shiraz wine. (February 2023)

• Record Type: Journal Article
• Authors: Ranaweera, Ranaweera K.R.; Bastian, Susan E.P.; Gilmore, Adam M.; Capone, Dimitra L.; Jeffery, David W.
• Is Part Of: Food control. Volume 144(2023)
• Publication Date: 2023-02
• Subjects: Extreme gradient boosting -- Terroir -- Subregion -- Authentication -- Provenance; A-TEEM absorbance-transmission and fluorescence excitation-emission matrix -- CA cluster analysis -- DA discriminant analysis -- GI Geographical Indication -- ICP-MS inductively coupled plasma-mass spectrometry -- LDA linear discriminant analysis -- PCA principal component analysis -- PLSDA partial least squares discriminant analysis -- SVM support vector machine -- PDO Protected Designation of Origin -- PGI Protected Geographical Indication -- XGB extreme gradient boosting -- XGBDA extreme gradient boosting discriminant analysis; Food -- Quality -- Periodicals; Food -- Analysis -- Periodicals; Food handling -- Periodicals; Food industry and trade -- Quality control -- Periodicals; Aliments -- Industrie et commerce -- Qualité -- Contrôle -- Périodiques; Aliments -- Qualité -- Périodiques; Aliments -- Analyse -- Périodiques; Hygiène alimentaire -- Périodiques; Food -- Analysis; Food handling; Food -- Quality; Periodicals; Electronic journals; 664.07
• DOI: 10.1016/j.foodcont.2022.109335
• Languages: English
• ISSNs: 0956-7135

Abstract

Abstract: Authentication of wine can be considered at different scales, with classification according to country, province/state, or appellation/wine producing region. An absorbance-transmission and excitation-emission matrix (A-TEEM) technique was applied for the first time to examine intraregional differences, using Shiraz wines (n = 186) produced during three vintages from five subregions of Barossa Valley and from Eden Valley. Absorption spectra and EEM fingerprints were modelled as a multi-block data set for initial exploration with k-means cluster analysis and principal component analysis, and then with machine learning modelling using extreme gradient boosting discriminant analysis (XGBDA). Whereas some clustering was evident with the initial unsupervised approaches, classification with XGBDA afforded an impressive 100% correct class assignment for subregion and vintage year. Extending the utility and novelty of the A-TEEM approach, predictive models for chemical parameters (alcohol, glucose + fructose, pH, titratable acidity, and volatile acidity) were also validated using A-TEEM data with XGB regression. Graphical abstract: Image 1 Highlights: Shiraz wine subregion and vintage modelled with multi-block analysis of A-TEEM data. Classification by unsupervised and supervised machine learning techniques explored. Fingerprints from A-TEEM may be applied to the verification of subregional terroirs. A-TEEM can be used to simultaneously predict the basic chemical parameters of wine.