Breeding technologies exploiting marker-assisted selection have accelerated the selection of new cross-bred pathogen-resistant grapevine varieties. Several genotypes have been patented and admitted to cultivation; however, while their tolerance to fungal diseases has been the object of several in vitro and field studies, their productive and fruit composition traits during ripening are still poorly explored, especially in warm sites. In this study, five white pathogen-resistant varieties (PRVs) listed as UD 80–100, Soreli, UD 30–080, Sauvignon Rytos, Sauvignon Kretos were tested over two consecutive seasons in a site with a seasonal heat accumulation of about 2000 growing degree days (GDDs), and their performances were compared to two Vitis vinifera L. traditional varieties, Ortrugo and Sauvignon Blanc. Berries were weekly sampled from pre-veraison until harvest to determine total soluble solids (TSS) and titratable acidity (TA) dynamics. All tested PRV exhibited an earlier onset of veraison and a faster sugar accumulation, as compared to Ortrugo and Sauvignon Blanc, especially in 2019. At harvest, Sauvignon Blanc was the cultivar showing the highest titratable acidity (8.8 g/L). Ortrugo and PRV varieties showed very low TA (about 4.7 g/L), with the exception of Sauvignon Rytos (6.5 g/L). However, data disclose that Sauvignon Rytos higher acidity at harvest relies on higher tartrate (+1.1 to +2.2 g/L, as compared to other PRV), whereas in Sauvignon Blanc, high TA at harvest is due to either tartaric (+1 g/L, compared to PRV) and malic (+2.5 g/L, compared to PRV) acid retention. Overall, Sauvignon Rytos is the most suited PRV to be grown in a warm climate, where retaining adequate acidity at harvest is crucial to produce high-quality white wines. Nevertheless, canopy and ripening management strategies must be significantly adjusted, as compared to the standard practice employed for the parental Sauvignon Blanc.
Even though mechanization has dramatically decreased labor requirements, vineyard management costs are still affected by selective operations such as winter pruning. Robotic solutions are becoming more common in agriculture, however, few studies have focused on grapevines. This work aims at fine-tuning and testing two different deep neural networks for: (i) detecting pruning regions (PRs), and (ii) performing organ segmentation of spur-pruned dormant grapevines. The Faster R-CNN network was fine-tuned using 1215 RGB images collected in different vineyards and annotated through bounding boxes. The network was tested on 232 RGB images, PRs were categorized by wood type (W), orientation (Or) and visibility (V), and performance metrics were calculated. PR detection was dramatically affected by visibility. Highest detection was associated with visible intermediate complex spurs in Merlot (0.97), while most represented coplanar simple spurs allowed a 74% detection rate. The Mask R-CNN network was trained for grapevine organs (GOs) segmentation by using 119 RGB images annotated by distinguishing 5 classes (cordon, arm, spur, cane and node). The network was tested on 60 RGB images of light pruned (LP), shoot-thinned (ST) and unthinned control (C) grapevines. Nodes were the best segmented GOs (0.88) and general recall was higher for ST (0.85) compared to C (0.80) confirming the role of canopy management in improving performances of hi-tech solutions based on artificial intelligence. The two fine-tuned and tested networks are part of a larger control framework that is under development for autonomous winter pruning of grapevines.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.