How sensor technologies combined with artificial intelligence increase the efficiency in grapevine breeding (research): current developments and future perspectives

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.

Knowledge of the nitrogen nutrition status of grapevines is essential for the sustainable management of their nutrition for the production of quality grapes. The measurement of the chlorophyll index is a rapid, non-destructive and relatively inexpensive method that provides a good approximation of the nitrogen nutrition status of the vine during the season. Interpretation thresholds are currently insufficient or non-existent for some chlorophyll meters. Ideally, they should be available for each variety and each phenological stage. In order to popularize the use of chlorophyll-meters, measurements were carried out at Agroscope in Switzerland to establish the correlation between the indices obtained by the devices N-tester and SPAD 502.

Vineyards face climate change, increasing temperatures, and drought affecting vine water status. Water deficit affects plant physiology and can ultimately decrease yield and grape quality when it is not well managed. Monitoring vine water status and irrigation can help growers better manage their vineyards.

The ’Furmint’ is the most important grape variety in the Tokaj Wine Region, constituting around 65% of its vineyard area. Before the phylloxera disease many types were grown, but as selection started in the 20th century, its diversity dramatically narrowed. As a result, the cultivation of Furmint was based mainly on two heavy-cropping clones, T.85 and T.92 at the end of the ’80s. Aims of present clone research take into account that after solely quantity as target, quality emerged in the 1990’s and most recently, typicity appeared as more private estates began their own selection program.

Dans le cadre de TerclimPro 2025, Laure Gontier a présenté un article IVES Technical Reviews. Retrouvez la présentation ci-dessous ainsi que l’article associé : https://ives-technicalreviews.eu/article/view/8481