Macrowine 2021
IVES 9 IVES Conference Series 9 Prediction of sauvignon blanc quality gradings with static headspace−gas chromatography−ion mobility spectrometry (SHS−GC−IMS) and machine learning

Prediction of sauvignon blanc quality gradings with static headspace−gas chromatography−ion mobility spectrometry (SHS−GC−IMS) and machine learning

Abstract

AIM: The main goal of the current study is the development of a cost-effective and easy-to-use method suitable for use in the laboratory of commercial wineries to analyze wine aroma. Additionally, this study attempted to establish a prediction model for wine quality gradings based on their aroma, which could reveal the important aroma compounds that correlate well with different grades of perceived quality

METHODS: Parameters of the SHS−GC−IMS instrument were first optimized to acquire the most desirable chromatographic resolution and signal intensities. Method stability was then exhibited by repeatability and reproducibility. Subsequently, compound identification was conducted. After method development, a total of 143 end-ferment wine samples of three different quality gradings from vintage 2020 were analyzed with the SHS−GC−IMS instrument. Six machine learning methods were employed to process the results and construct a quality prediction model. Techniques that aim to explain the model to extract useful insights were also applied.

RESULTS: The SHS−GC−IMS method was able to detect 23 compounds among 65 peaks, mostly esters and higher alcohols, using the current instrumentation. Several identified compounds, including methyl acetate, ethyl formate, and amyl acetate, have seldomly been reported in Sauvignon Blanc wines before. The method also indicated decent repeatability and reproducibility, both of which were below 10%. The quality prediction model was successfully established using artificial neural network (ANN) based on all peaks regardless of their identity. The model returned a highly satisfactory prediction accuracy of 95.4% using 10-fold cross-validation. SHapley Additive exPlanations (SHAP) values was used to delineate the prediction mechanism of the model. SHAP values revealed that isoamyl acetate, ethyl decanoate, ethyl octanoate and 1-hexanol were positively linked to better quality, whereas hexyl acetate, isoamyl alcohol, and 1-butanol could lower the quality grading.

CONCLUSIONS:

This study has successfully developed a method alternative to GC−MS based instruments for the non-targeted screening of wine volatile compounds. With its simple design featuring a headspace sampling unit, highly simplified sample preparation, and nitrogen being the only gas supply, the instrument has shown outstanding practicality desired by commercial winery laboratories. The powerful prediction model and the insights extracted by SHAP values could serve as a starting point for winemakers to investigate the effects of winemaking operations on the expression of the volatiles shown to correlate with higher gradings, to enhance the quality of wines. The findings of this study have been published as an original research article in the Journal of Agricultural and Food Chemistry: J. Agric. Food Chem. 2021, 69(10), 3255−3265.

DOI:

Publication date: September 22, 2021

Issue: Macrowine 2021

Type: Article

Authors

Wenyao Zhu , Frank BENKWITZ, Paul A. KILMARTIN,

School of Chemical Sciences, University of Auckland, Private Bag 92019, Auckland, New Zealand; Drylands Winery, Constellation Brands NZ, Blenheim 7273, New Zealand.

Contact the author

Keywords

Sauvignon blanc, static headspace−gas chromatography−ion mobility spectrometry (SHS−GC−IMS), quality grading, machine learning, artificial neural network (ANN), model explanation

Citation

Related articles…

A NEW TOOL TO QUANTIFY COMPOUNDS POTENTIALLY INVOLVED IN THE FRUITY AROMA OF RED WINES. DEVELOPMENT AND APPLICATION TO THE STU-DY OF THE FRUITY CHARACTER OF RED WINES MADE FROM VARIOUS GRAPE VARIETIES

A wide range of olfactory descriptors ranging from fresh and jammy fruit notes to cooked and oxidized fruit notes could describe the fruity aroma of red wines [1]. The fruity character of a wine is mainly related to the grape variety selected, to the terroir and the vinification process applied for its conception. In white wines, some volatile compounds confer directly their aroma to the wine while the question of “key” compound is more complex in red wines. According to many studies performed over the past decades, some fruity ethyl esters are directly involved in the fruity perception of red wines while others, present at subthreshold concentrations, participate indirectly to the fruity expression via perceptive interactions [2].

Sensory profile: a tool to characterize originality of wines produced without sulfites

A trend to reduce chemical inputs in wines exists, especially sulfur dioxide (SO2). This additive is widely used due to its antioxidant, antiseptic and antioxidasic properties. During without sulfites vinification, bioprotection by adding yeast on harvest could be a sulfites alternative. With extension of this wine market, sensory impact linked to sulfites absence and/or sulfites alternative should be evaluated. That’s what this approach proposes to do, focusing on sensory characteristics of wines produced with or without SO2 addition during the winemaking process. METHODS: Wines were elaborated from Merlot grapes of two maturity levels according to three modalities: SO2, without SO2 and bioprotection on harvest (mix of Torulaspora delbrueckii and Metschnikowia pulcherrima). SO2 modality was sulfited throughout the winemaking and aging processes whether other modalities received any addition. After two years of aging, sensory studies were carried out with a specific panel for one month. First, descriptors were generated to differentiate the wines, then panelists were trained on these specific descriptors for five sessions and finally wines sensory profiles were elaborated

Oligosaccharides from Vitis vinifera grape seeds: a focus on gentianose as a novel bioactive compound

AIM. Grape seeds (Vitis vinifera) are among the main constituents of grape pomace, also exploited in ingredients for nutraceutics and cosmeceutics, particularly regarding the phenolic fraction. The macromolecules of grape/wine include polyphenols, proteins and polysaccharides.

FERMENTATION POTENTIAL OF INDIGENOUS NON-SACCHAROMYCES YEASTS ISOLATED FROM MARAŠTINA GRAPES OF CROATIAN VINEYARDS

The interest in indigenous non-Saccharomyces yeast for use in wine production has increased in recent years because they contribute to the complex character of the wine. The aim of this work was to investigate the fermentation products of ten indigenous strains selected from a collection of native yeasts established at the Institute for Adriatic Crops and Karst Reclamation in 2021, previously isolated from Croatian Maraština grapes, belonging to Hypopichia pseudoburtonii, Metschnikowia pulcherrima, Metschnikowia sinensis, Metschnikowia chrysoperlae, Lachancea thermotolerans, Pichia kluyveri, Hanseniaspora uvarum, Hanseniaspora guillermondii, Hanseniaspora pseudoguillermondii, and Starmerella apicola species, and compare it with commercial non-Saccharomyces and Saccharomyces strains.

Analysis of off flavours in grapes infected with the fungal bunch rot pathogens, Aspergillus, Botrytis and Pencillium

Fungal bunch rots of grapes cause major losses to grape yield worldwide, yet the impact these moulds have on grape and wine quality is not well characterised. We sought to investigate the formation of unwanted volatile compounds of fungal origin in both synthetic grape juice culture media and in inoculated grape berries. Botrytis cinerea, Aspergillus niger, Aspergillus carbonarius, or Pencillium expansum were grown in synthetic grape juice medium and the culture homogenates analysed 4 and 7 days post inoculation. HS-SPME-GC-MS analysis of the culture homogenates 4 days post inoculation demonstrated that each of the fungi examined produced varying quantities of the mushroom or fungus-like aroma compounds, 1-Octen-3-ol, 1-Octen-3-one and 3-Octanone with A. carbonarius producing up to ten times the amounts of all three metabolites per mg of dry mycelium.