High-resolution aerial thermography for water stress estimation in grapevines

According to the different concern of the ‘traditional’ and the ‘new’ wine-producing Countries, a variable importance is recognized to the climate/soil and to grapevine cultivars as factors affecting the wine quality. However, the viticultural experience can state that, within each area, climate and soil plays an incontestable role in affecting grape quality, and consequently wine quality, as well as the genetic characteristics of the cultivar.

Bioprotection, leveraging beneficial microorganisms, has emerged as a sustainable approach to modern winemaking, minimizing reliance on chemical preservatives like as sulfur dioxide (SO₂).

The quality of wine is difficult to define. This is most certainly accredited to everyone´s different perception of quality. Some of the indicators of high-quality wines are complexity, balance, color and intensity. Color is one of the most crucial attributes of quality, not only for the obvious implications for their perception but also because they are indicators of other aspects related to its aroma and taste. Phenolic compounds are the main responsible for wine color, being anthocyanin and tannins the most determinant compounds in red wines. In addition to color, wine aroma is another important attribute linked with quality and consumer preferences.

Aim: In this work, we have optimized a robust methodology for investigating possible correlations between the phytochemical profile of wine and the terroir (including the climate), considering the specific wine-growing area. In particular, the untargeted metabolomic and sensorial profiles of Gutturnio DOC commercial wines (both still and “frizzante” types) from different production areas in the Piacenza province were determined. The geographical areas taken into consideration for this study consisted in Val Tidone, Val Nure and Val d’Arda.

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.