WAC 2022 banner
IVES 9 IVES Conference Series 9 WAC 9 WAC 2022 9 3 - WAC - Oral 9 Accurate Quantification of Quality Compounds and Varietal Classification from Grape Extracts using the Absorbance-Transmittance Fluorescence Excitation Emission Matrix (A-TEEM) Method and Machine Learning

Accurate Quantification of Quality Compounds and Varietal Classification from Grape Extracts using the Absorbance-Transmittance Fluorescence Excitation Emission Matrix (A-TEEM) Method and Machine Learning

Abstract

Rapid and accurate quantification of grape berry phenolics, anthocyanins and tannins, and identification of grape varieties are both important for effective quality control of harvesting and initial processing for wine making. Current reference technologies including High Performance Liquid Chromatography (HPLC) can be rate limiting and too complex and expensive for effective field operations. Secondary calibrated techniques including UV-VIS and Near and Mid Infrared spectroscopy are insensitive to specific quality compounds and unable to make accurate varietal assignments. In this paper we analyze robotically prepared grape extracts from several key varieties (n=Calibration/p=Prediction samples) including Cabernet sauvignon (64/10), Grenache (16/4), Malbec (14/4), Merlot (56/10), Petit syrah (52/10), Pinot noir (54/8), Syrah (20/2), Terlodego (14/2) and Zinfandel (62/12). Key phenolic and anthocyanin parameters measured by HPLC included Catechin, Epicatechin, Quercetin Glycosides, Malvidin 3-glucoside, Total Anthocyanins and Polymeric Tannins. Separate samples diluted 150 fold in 50% EtOH pH 2 were analyzed in parallel using the A-TEEM method following Multiblock Data Fusion of the absorbance and unfolded EEM data. A-TEEM chemical data were calibrated (n=390) using Extreme Gradient Boost (XGB) Regression and evaluated based on the Root Mean Square Error of the Prediction (RMSEP), the Relative Error of Prediction (REP%) and Coefficient of Variation (R2P) of the Prediction data (n=62). The regression results yielded an average REP% value of 6.0±2.4% and R2P of 0.941±0.024. While we consider the REP% values to be in the acceptable range at <10% we acknowledge that both the grape extraction method repeatability and HPLC reference method repeatability likely contributed the major sources of variation; e.g., A-TEEM sample REP%=1.31 for Polymeric Tannins. Varietal classification was analyzed using XGB discrimination analysis of the Multiblock data and evaluated based on the Prediction data. The classification results yielded 100% True Positive and True negative results for the Prediction Data for all varieties. We conclude that the A-TEEM method requires a minimum of sample preparation and rapid acquisition times (<1 min) and can serve as an accurate secondary method for both grape composition and varietal identification. Importantly, the application of the regression and classification models can be effectively automated for operators.

DOI:

Publication date: June 13, 2022

Issue: WAC 2022

Type: Article

Authors

Adam, Gilmore, Qiang, Sui

Presenting author

Adam, Gilmore – HORIBA Instruments Inc.

E & J Gallo Wines

Contact the author

Keywords

Extreme Gradient Boost – Phenolics – Anthocyanins- Tannins-Grape Variety

Tags

IVES Conference Series | WAC 2022

Citation

Related articles…

La zonazione viticola e i compiti dell’amministrazione regionale

Solo attraverso un adeguato intervento di estirpazione e reimpianto dei vigneti è possibile preservare, adeguare e valorizzare il patrimonio viticolo e le produzioni che da esso derivano.
Il reimpianto dei vigneti è pertanto da intendersi come una normale pratica agricola, alla pari della rimonta di stalla in campo zootecnico, ma può assumere toni problematici quando, come si verifica adesso in Toscana per una serie di circostanze legate alla profonda trasfor­mazione della viticoltura avvenuta negli ultimi 30 anni, troppi impianti giungono contem­poraneamente a fine ciclo produttivo e devono essere rinnovati.

D-wines: use of LC-MS metabolomic space to discriminate italian mono-varietal red wines

Studying wine metabolome through multiple targeted methods is complicated and limitative; since grapes, yeasts, bacteria, oxygen, enological techniques and wine aging collaborate to deliver one of the richest metabolomic fingerprint.

Investigation of the effect of gelatine and egg albumin fining and cross-flow microfiltration on the phenolic composition of Pinotage red wine

Results indicated that cross-flow microfiltration removed similarly to fining treatments the most astringent tannins, but cross-flow microfiltration also removed up to 14 % more colour. RP-HPLC and spectrophotometric results showed that egg albumin is a softer fining treatment compared to gelatine and cross-flow microfiltration.

Mathematical modeling of fermentation kinetics: a tool to better understand interactions between Torulaspora delbrueckii and Saccharomyces cerevisiae in mixed cultures

Nowadays the use of Torulaspora delbrueckii is more and more common in winemaking. However, its behavior in presence of Saccharomyces cerevisiae is not always predictable.

Satellite imagery : a tool for large scale vineyard management

Remote sensing, using Near Infra Red wavelength, can characterize within-vineyard variability using vegetation index. Between 2007 and 2009, a study was led on the vineyards of a cooperative winery, in Fitou area (France) aiming at characterizing vineyard oenological potential. A vegetation index, green leaf cover, developed on crops (wheat, rice, corn…) was implemented on vineyards.