Wine tannins: What place for grape seed?

Managing grapevines according to the practices of Precision Agriculture (PA), may prove to be an asset in the hands of the modern grape growers.

Context and purpose of the study. Modern conventional agriculture, including viticulture, relies greatly on the use of chemical inputs, especially synthetic pesticides.

Typically, subjective, and visual methods are used by grape growers to assess harvest maturity. These methods may not accurately represent the maturity of an entire vineyard – especially if extensive and representative sampling was not used. New technologies have been investigated for improved harvest management decisions. Spectroscopy methods utilizing the near-infrared region of the light spectrum is one such technology investigated as an alternative to classic methods and particularly the application of hyperspectral imaging (HSI) has recently gained attention in research. HIS is a spectroscopic technique that obtains hundreds of images at different wavelengths collecting spectral data for each pixel in the sample i.e., providing both spectral and spatial data.

A large varietal collection including over 1700 varieties was maintained in Conegliano, ITA, since the 1950s. Phenological data on a subset of 400 grape varieties including wine grapes, table grapes, and raisins were acquired at bud break, flowering, veraison, and ripening since 1964. Despite the efforts in maintaining and acquiring data over such an extensive collection, the data set has varying degrees of missing cases depending on the variety and the year. This is ubiquitous in phenology datasets with significant size and length. In this work, we evaluated four state-of-the-art methods to estimate missing values in this phenological series: k-Nearest Neighbour (kNN), Multivariate Imputation by Chained Equations (mice), MissForest, and Bidirectional Recurrent Imputation for Time Series (BRITS). For each phenological stage, we evaluated the performance of the methods in two ways. 1) On the full dataset, we randomly hold-out 10% of the true values for use as a test set and repeated the process 1000 times (Monte Carlo cross-validation). 2) On a reduced and almost complete subset of varieties, we varied the percentage of missing values from 10% to 70% by random deletion. In all cases, we evaluated the performance on the original values using normalized root mean squared error. For the full dataset we also obtained performance statistics by variety and by year. MissForest provided average errors of 17% (3 days) at budbreak, 14% (4 days) at flowering, 14.5% (7 days) at veraison, and 17% (3 days) at maturity. We completed the imputations of the Conegliano dataset, one of the world’s most extensive and varied phenological time series and a steppingstone for future climate change studies in grapes. The dataset is now ready for further analysis, and a rigorous evaluation of imputation errors is included.

In the maceration stage of winemaking, enzymes can be used to degrade the polysaccharides present in the cell walls and middle sheets, and thus facilitate the extraction of juice and the release of polyphenols and aroma precursors retained in the grape skins.