The importance of outlier rejection and significant explanatory variable selection for pinot noir wine soft sensor development

Sensory attributes are essential factors in determining the quality of wines. However, it can be challenging for consumers, even experts, to differentiate and quantify wines' sensory attributes for quality control. Soft sensors based on rapid chemical analysis offer a potential solution to overcome this challenge. However, the current limitation in developing soft sensors for wines is the need for a significant number of input parameters, at least 12, necessitating costly and time-consuming analyses. While such a comprehensive approach provides high accuracy in sensory quality mapping, the expensive and time-consuming studies required do not lend themselves to the industry's routine quality control activities. In this work, Box plots, Tucker-1 plots, and Principal Component Analysis (PCA) score plots were used to deal with output data (sensory attributes) to improve the model quality. More importantly, this work has identified that the number of analyses required to fully quantify by regression models and qualify by classification models can be significantly reduced. Based on regression models, only four key chemical parameters (total flavanols, total tannins, A_520nm^HCl, and pH) were required to accurately predict 35 sensory attributes of a wine with R² values above 0.6 simultaneously. In addition, for classification models to accurately predict 35 sensory attributes of a wine at once with prediction accuracy above 70%, only four key chemical parameters (A_280nm^HCl, A_520nm^HCl, chemical age and pH) were required. These models with reduced chemical parameters complement each other in sensory quality mapping and provide acceptable accuracy. The application of the soft sensor based on these reduced sets of key chemical parameters translated to a potential reduction in analytical cost and labour cost of 56% for the regression model and 83% for the classification model, respectively, making these models suitable for routine quality control use.

Could Collected Chemical Parameters Be Utilized to Build Soft Sensors Capable of Predicting the Provenance, Vintages, and Price Points of New Zealand Pinot Noir Wines Simultaneously?

Soft sensors work as predictive frameworks encapsulating a set of easy-to-collect input data and a machine learning method (ML) to predict highly related variables that are difficult to measure. The machine learning method could provide a prediction of complex unknown relations between the input data and desired output parameters. Recently, soft sensors have been applicable in predicting the prices and vintages of New Zealand Pinot noir wines based on chemical parameters. However, the previous sample size did not adequately represent the diversity of provenances, vintages, and price points across commercially available New Zealand Pinot noir wines. Consequently, a representative sample of 39 commercially available New Zealand Pinot noir wines from diverse provenances, vintages, and price points were selected. Literature has shown that wine phenolic compounds strongly correlated with wine provenances, vintages and price points, which could be used as input data for developing soft sensors. Due to the significance of these phenolic compounds, chemical parameters, including phenolic compounds and pH, were collected using UV-Vis visible spectrophotometry and a pH meter. The soft sensor utilising Naive Bayes (belongs to ML) was designed to predict Pinot noir wines' provenances (regions of origin) based on six chemical parameters with the prediction accuracy of over 75%. Soft sensors based on decision trees (within ML) could predict Pinot noir wines' vintages and price points with prediction accuracies of over 75% based on six chemical parameters. These predictions were based on the same collected six chemical parameters as aforementioned.

Wineinformatics: Comparing and Combining SVM Models Built by Wine Reviews from Robert Parker and Wine Spectator for 95 + Point Wine Prediction

Wineinformatics is among the new fields in data science that use wine as domain knowledge. To process large amounts of wine review data in human language format, the computational wine wheel is applied. In previous research, the computational wine wheel was created and applied to different datasets of wine reviews developed by Wine Spectator. The goal of this research is to explore the development and application of the computational wine wheel to reviews from a different reviewer, Robert Parker. For comparison, this research collects 513 elite Bordeaux wines that were reviewed by both Robert Parker and Wine Spectator. The full power of the computational wine wheel is utilized, including NORMALIZED, CATEGORY, and SUBCATEGORY attributes. The datasets are then used to predict whether the wine is a classic wine (95 + scores) or not (94 − scores) using the black-box classification algorithm support vector machine. The Wine Spectator’s dataset, with a combination of NORMALIZED, CATEGORY, and SUBCATEGORY attributes, achieves the best accuracy of 76.02%. Robert Parker’s dataset also achieves an accuracy of 75.63% out of all the attribute combinations, which demonstrates the usefulness of the computational wine wheel and that it can be effectively adopted in different wine reviewers’ systems. This paper also attempts to build a classification model using both Robert Parker’s and Wine Spectator’s reviews, resulting in comparable prediction power.