Grape variety identification and detection of terroir effects from satellite images

For coopers, toasting process is considered a crucial step in barrel production during which oak wood (Q. petraea) develops several aromatic nuances released to the wine during its maturation. Toasting consists of applying different degrees of heat to a barrel for a specific period. As the temperature increases, thermal degradation of oak wood structure produces a huge range of chemical compounds. Many studies have identified the main key aroma volatile compounds (whisky-lactone, furfural, eugenol, guaiacol, vanillin). However, detailed information on how the chemical structure of oak wood degrades with increasing toasting level is still lacking.

In this study, a soil mapping methodology at subplot level (scale 1:5000) for vineyard soils was developed. The aim of this mapping method was to establish mapping units, which could be used as basic units for ‘terroir’ characterisation and vineyard management (precision viticulture).

AIM: The composition and quality of wine are directly linked to microorganisms involved in the alcoholic fermentation. Several studies have been conducted on the impact of Saccharomyces cerevisiae on volatile compounds composition after fermentation. However, if different studies have dealt with combined sensory and volatiles analyses, few works have compared so far the impact of distinct yeast strains on the global metabolome of the wine.

Wine quality is defined by sensory and physico-chemical characteristics. In particular, sensory features are very important since they strongly condition wine acceptability by consumers. However, the evaluation of sensory quality can be subjective, unless performed by a tasting panel of experienced tasters. Therefore, it is of great relevance to establish relationships between objective chemical parameters and sensory perceptions, even though the complexity of wine composition makes it difficult. In this sense, more reliable relationships can be found for a particular wine typology or variety. The present study aimed to predict the perceived sensory quality from the physico-chemical parameters of ‘Barbera d’Asti’ DOCG red wines (Italy).

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.