A new AI-based system for early and accurate vineyard yield forecasting

Clay-based ceramic vessels (jars, pyhtoi, etc.) for wine fermentation and aging processes have been used in several cultures for millennia. This know-how still in practice in several countries of the Armenian highland is gaining worldwide in curiosity, popularity, and interest. Ceramic pots are famous among traditional winemakers for their benefits such as temperature regulation, natural cooling system, favorable oxygen exchange, and impact on pH, which are different from those of stainless steel, wood barrels, or concrete.

Glutathione is a natural tripeptide composed of l-glutamate, l-cysteine and glycine, found in various foods and beverages. In particular, glutathione can be found in its reduced (GSH) or oxidized form (GSSG) in must, wine or yeasts¹. Numerous studies have highlighted the importance of GSH in wine quality and aging potential². During winemaking, especially during aging on lees, GSH helps prevent the harmful effects of oxidation on the aroma of the wine³. Nevertheless, the amounts of GSH/GSSG present in wine lees are often unknown and the choice of operating conditions (quantity of lees and aging time) remains empirical.

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.

Aims: The objective of this research was to analyse the spatial and temporal variability of vine phenology of the Tempranillo variety in the Toro Designation of Origen (DO) related to climatic conditions at present and under future climate change scenarios.

Egri Bikavér (Bull’s Blood) is one of the most remarkable Hungarian red wines on inland and foreign markets as well. From the end of the 70’s the quality of Egri Bikavér was decreasing continually due to mass production. The concept of production of quality wines became general in the mid 90’s again and it resulted in a new Origin Control System, for the first time that of Egri Bikavér in Hungary.