 IVES 9 IVES Conference Series 9 Fluorescence spectroscopy with xgboost discriminant analysis for intraregional wine authentication

Fluorescence spectroscopy with xgboost discriminant analysis for intraregional wine authentication

Abstract

AIM: This study aimed to use simultaneous measurements of absorbance, transmittance, and fluorescence excitation-emission matrix (A-TEEM) combined with chemometrics as a rapid method to authenticate wines from three vintages within a single geographical indication (GI) according to their subregional variations.

METHODS: The A-TEEM technique (Gilmore, Akaji, & Csatorday, 2017) has been applied to analyse experimental Shiraz wines (n = 186) from six subregions of Barossa Valley, South Australia, from 2018, 2019 and 2020 vintages. Absorbance spectra and EEM fingerprints of the wines were recorded and the data were fused for multivariate statistical modelling with extreme gradient boost discriminant analysis (XGBDA) as reported by Ranaweera, Gilmore, Capone, Bastian, and Jeffery (2021) to classify wine according to their subregions. The cross-validated (k =10, Venetian blinds) confusion matrix score probabilities of classes were used to assess the accuracy of the classification models. A similar procedure was also carried out to discriminate subregions for a single vintage year. Basic chemical parameters (alcohol %v/v, pH, titratable acidity, and volatile acidity) were modelled with the partial least squares regression (PLSR) using A-TEEM data and reference chemical data.

RESULTS: Results have shown an unprecedented 100% correct classification of wines according to subregion across the three vintages and 98% accuracy for subregion in a single vintage year. Other model performance parameters of confusion matrix, including sensitivity, specificity, precision, and F1 score, were also showing the highest values (1.0) for each of the subregions. PLSR modelling revealed that A-TEEM data can also be used for a rapid assessment of basic wine chemical parameters. Notably, the results confirmed a distinct resolution among subregions despite their relatively close proximity within a single GI, indicating the effect of terroir on intraregional variation.

CONCLUSIONS

The sensitivity of A-TEEM allied with multivariate statistical analysis of fluorescence data facilitated the accurate classification of Shiraz wines according to the subregion of origin and production year. As a robust analytical method, A-TEEM can help identify the drivers of regional expression of wine and can potentially be developed for use within the supply chain to guarantee the provenance indicated on the label and to provide an assurance of quality. Overall, A-TEEM with XGBDA modelling continues to be shown as an accurate wine authentication tool that could even be applied at a subregional level.

DOI:

Publication date: September 7, 2021

Issue: Macrowine 2021

Type: Article

Authors

Ruchira Ranaweera

Department of Wine Science, The University of Adelaide, South Australia, Australia,Adam GILMORE, Horiba Instruments Inc., Piscataway, New Jersey, USA Dimitra CAPONE, The Australian Research Council Training Centre for Innovative Wine Production, The University of Adelaide Susan BASTIAN, The Australian Research Council Training Centre for Innovative Wine Production, The University of Adelaide David JEFFERY, The Australian Research Council Training Centre for Innovative Wine Production, The University of Adelaide

Contact the author

Keywords

geographical indication, authenticity, subregion, excitation-emission matrix, chemometrics, terroir

Citation

Evaluating the greenness of wine analytical chemistry: A new metric approach

Wine is a complex matrix whose composition depends on climatic, agricultural, and winemaking factors, making quality control and authenticity assessment critical in the global market.

Identification of caffeic acid as a major component of Moscatel wine protein sediment

Proteins play a significant role in the colloidal stability and clarity of white wines [1]. However, under conditions of high temperatures during storage or transportation, the proteins themselves can self-aggregate into light-dispersing particles causing the so-called protein haze [2]. Formation of these unattractive precipitates in bottled wine is a common defect of commercial wines, making them unacceptable for sale [3]. Previous studies identified the presence of phenolic compounds in the natural precipitate of white wine [4], contributing to the hypothesis that these compounds could be involved in the mechanism of protein haze formation.

Building of a hierarchy of wines based on terroirs: an initiative from the producers of Muscadet

The Muscadet area is situated in the southeast of Nantes, close to the Atlantic coast. It constitutes the western extension
of the French vineyard “Loire Valley”. The Muscadet is renowned and often spontaneously linked to a white wine.
However it remains misconceived as an ordinary wine, lacking authenticity.

Integration of wine cultivation history for characterizing the terroirs of Côte d’Or (Burgundy, France)

Les aires d’appellations de la Côte d’Or résultent d’une sélection humaine empirique, historique et évolutive en adéquation avec les facteurs naturels. Afin de comprendre quels facteurs naturels et humains agissent sur le caractère et l’évolution des terroirs des Côtes de Nuits et de Beaune, une méthodologie de recherche a été développée. Elle s’articule autour de deux axes, la caractérisation physique des lieux-dits viticoles et l’historicité de la qualité de ces lieux-dits. Le travail avec un S.I.G permet d’étudier l’évolution spatiale et temporelle de la qualité.

Dormancy conundrum: thermal requirements plasticity to reach budburst may be explained by annual environmental dynamics

Deciphering grapevine dormancy is crucial in the current context of climatic challenges: advancing budburst phenology and increased late frost probabilities, observed in the last decades and expected to further increase, require deeper understanding. Beyond higher mean temperatures, abiotic stresses such as water deficit have also been emphasized as actors. In this framework, we aimed at exploring new methodologies for tracking dormancy cycle and testing the interplay on its regulation of temperature dynamics and drought.
In a first experiment, twenty-one Vitis vinifera varieties were monitored during ecodormancy and budburst over three years.