Alcoholic Fermentation Monitoring and pH Prediction in Red and White Wine by Combining Spontaneous Raman Spectroscopy and Machine Learning Algorithms

被引:6
|
作者
Fuller, Harrison [1 ]
Beaver, Chris [1 ]
Harbertson, James [1 ]
机构
[1] Washington State Univ, St Michelle Wine Estates WSU Wine Sci Ctr, Sch Food Sci, Coll Agr Human & Nat Resource Sci, 359 Univ Dr, Richland, WA 99354 USA
来源
BEVERAGES | 2021年 / 7卷 / 04期
关键词
Raman spectroscopy; predictive modeling; machine learning; regression; enology; winemaking; PHENOLIC-COMPOUNDS; DISCRIMINATION; ANTHOCYANINS; ETHANOL; QUANTIFICATION; IDENTIFICATION; ADULTERATION; COMPONENTS; PIGMENTS; METHANOL;
D O I
10.3390/beverages7040078
中图分类号
TS2 [食品工业];
学科分类号
0832 ;
摘要
In the following study, total sugar concentrations before and during alcoholic fermentation, as well as ethanol concentrations and pH levels after fermentation, of red and white wine grapes were successfully predicted using Raman spectroscopy. Fluorescing compounds such as anthocyanins and pigmented phenolics found in red wine present one of the primary limitations of enological analysis using Raman spectroscopy. Unlike the spontaneous Raman effect, fluorescence is a highly efficient process and consequently emits a much stronger signal than spontaneous Raman scattering. For this reason, many enological applications of Raman spectroscopy are impractical as the more subtle Raman spectrum of any red wine sample is in large part masked by fluorescing compounds present in the wine. This work employs a simple extraction method to mitigate fluorescence in finished red wines. Ethanol and total sugars (fructose plus glucose) of wines made from red (Cabernet Sauvignon) and white (Chardonnay, Sauvignon Blanc, and Gruner Veltliner) varieties were modeled using support vector regression (SVR), partial least squares regression (PLSR) and Ridge regression (RR). The results, which compared the predicted to measured total sugar concentrations before and during fermentation, were excellent (R-SVR(2) = 0.96, R-PLSR(2) = 0.95, R-RR(2) = 0.95, RMSESVR = 1.59, RMSEPLSR = 1.57, RMSERR = 1.57), as were the ethanol and pH predictions for finished wines after phenolic stripping with polyvinylpolypyrrolidone (R-SVR(2) = 0.98, R-PLSR(2) = 0.99, R-RR(2) = 0.99, RMSESVR = 0.23, RMSEPLSR = 0.21, RMSERR = 0.23). The results suggest that Raman spectroscopy is a viable tool for rapid and trustworthy fermentation monitoring.
引用
收藏
页数:11
相关论文
共 2 条
  • [1] Machine learning algorithms for in-line monitoring during yeast fermentations based on Raman spectroscopy
    Wu, Debiao
    Xu, Yaying
    Xu, Feng
    Shao, Minghao
    Huang, Mingzhi
    VIBRATIONAL SPECTROSCOPY, 2024, 132
  • [2] Diffuse reflectance mid infra-red spectroscopy combined with machine learning algorithms can differentiate spectral signatures in shallow and deeper soils for the prediction of pH and organic matter content
    de Santana, Felipe Bachion
    Grunsky, Eric C.
    Fitzsimons, Mairead
    Gallagher, Vincent
    Daly, Karen
    CATENA, 2022, 218