Hyperspectral imaging and machine learning for monitoring grapevine physiology

The sequential activity of miR156 and miR172 controls the juvenile to adult phase transition in many plant species, where miR156 abundance decreases while miR172 increases along plant development. Very little is known about phase transition in horticultural woody species, which show substantially long vegetative phases. In grapevine, phase transition seems to be dissociated, displaying a first transition from juvenile to adult vegetative state in the first year, coincident with tendril differentiation and a subsequent induction of inflorescences in place of some of tendrils in later years under flowering inductive environmental conditions. Since grapevine is a highly heterozygous species, the generation of genetically homogeneous material for replicated transcriptomic analyses from seed-derived plants was a main challenge.

Due to the current challenging nature of the global wine market, and recent growth in number and strength of competitors from non-traditional wine producing countries, European wine producers are focussing on the potential to develop a competitive advantage through the concept of terroir.

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.

Pinking of white wine is an undesired change potentially occurring over storage, leading to the turning of color from yellow into salmon-red hue.

Climate change is impacting wine production in all parts of the world in highly variable ways that may change the expression of terroir, from rapid loss of viability right through to highly beneficial aspects that increase suitability