Machine learning for classifying and predicting grape maturity indices using absorbance and fluorescence spectra. (1st March 2023)

• Record Type: Journal Article
• Authors: Armstrong, Claire E.J.; Gilmore, Adam M.; Boss, Paul K.; Pagay, Vinay; Jeffery, David W.
• Is Part Of: Food chemistry. Volume 403(2023)
• Publication Date: 2023-03-01
• Subjects: A-TEEM -- Chemometrics -- Data fusion -- Discriminant analysis -- Regression -- XGBoost; A-TEEM absorbance-transmission and fluorescence excitation-emission matrix -- CV cross-validation -- dpf days post flowering -- EEM excitation emission matrix -- IBMP 3-isobutyl-2-methoxypyrazine -- IPMP 3-isopropyl-2-methoxypyrazine -- IR infrared -- PARAFAC parallel factor analysis -- PLS partial least squares -- RMSE root mean square error -- RMSECV root mean square error cross-validation -- SBMP 3-sec-butyl-2-methoxypyrazine -- TSS total soluble solids -- XGB extreme gradient boosting -- XGBDA extreme gradient boosting discriminant analysis; Food -- Analysis -- Periodicals; Food -- Composition -- Periodicals; 664
• DOI: 10.1016/j.foodchem.2022.134321
• Languages: English
• ISSNs: 0308-8146

Abstract

Graphical abstract: Highlights: A rapid analytical method for the determination of grape maturity was developed. Absorbance and fluorescence data of Cabernet Sauvignon grape samples were fused. Indices for technological, flavour and phenolic maturity of grapes were predicted. Grape maturity was classified using XGBoost discriminant analysis algorithm. The method could aid decision making for harvest based on objective measures. Abstract: Absorbance-transmission and fluorescence excitation-emission matrix (A-TEEM) spectroscopy was investigated as a rapid method for predicting maturity indices using Cabernet Sauvignon grapes produced under four viticulture treatments during two growing seasons. Machine learning models were developed with fused spectral data to predict 3-isobutyl-2-methoxypyrazine (IBMP), pH, total tannins (Tannin), total soluble solids (TSS), and malic and tartaric acids based on the results from traditional analysis methods. Extreme gradient boosting (XGB) regression yielded R 2 values of 0.92–0.96 for IBMP, malic acid, pH, and TSS for externally validated (Test) models, with partial least squares regression being superior for TSS prediction (R 2 = 0.97). R 2 values of 0.64–0.81 were achieved with either approach for tartaric acid and Tannin predictions. Classification of grape maturity, defined by quantile ranges for red colour, IBMP, malic acid, and TSS, was investigated using XGB discriminant analysis, providing an average of 78 % correctly classified samples for the Test model.