Roberto Carraro

Dr. Roberto Carraro


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 February 2024 in The Journal of Agricultural Science
Verified
Journal Article
Open access
PDF file
DND. De Nart
D. De Nart
MGM. Gardiman
M. Gardiman
VAV. Alba
V. Alba
LTL. Tarricone
L. Tarricone
PSP. Storchi
P. Storchi
RCRoberto Carraro
Roberto Carraro
Varietal identification plays a pivotal role in viticulture for several purposes. Nowadays, such identification is accomplished using ampelography and molecular markers, techniques requiring specific expertise and equipment. Deep learning, on the other hand, appears to be a viable and cost-effective alternative, as several recent studies claim that computer vision models can identify different vine varieties with high accuracy. Such works, however, limit their scope to a handful of selected varieties and do not provide accurate figures for external data validation. In the current study, five well-known computer vision models were applied to leaf images to verify whether the results presented in the literature can be replicated over a larger data set consisting of 27 varieties with 26 382 images. It was built over 2 years of dedicated field sampling at three geographically distinct sites, and a validation data set was collected from the Internet. Cross-validation results on the purpose-built data set confirm literature results. However, the same models, when validated against the independent data set, appear unable to generalize over the training data and retain the performances measured during cross validation. These results indicate that further enhancement have been done in filling such a gap and developing a more reliable model to discriminate among grape varieties, underlining that, to achieve this purpose, the image resolution appears to be a crucial factor in the development of such models.

30 June 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
KMKASIPANDI MUNIYANDI
KASIPANDI MUNIYANDI
MRMirko De Rosso
Mirko De Rosso
RCRoberto Carraro
Roberto Carraro
GTGuy Tamir
Guy Tamir
KKKrishna Kumar
Krishna Kumar
IMItay Maoz
Itay Maoz
In this work, we examine the impact of elevated temperature during blueberry fruit ripening on the production and accumulation of anthocyanins, a key antioxidant. We profiled anthocyanins and the expression of their respective biosynthetic genes during ripening in two blueberry cultivars, Biloxi (Southern highbush) and Titan (Rabbiteye), across two seasons at controlled ripening temperatures (20 °C / 30 °C). We characterized 21 anthocyanins with diverse degrees of conjugation that remained largely stable in Titan between the two conditions. In Biloxi, cyanidin- and peonidin-derived anthocyanin signals were consistently reduced at 30 °C compared to 20 °C, corresponding with gene expression. Moreover, we found downregulation of VcF3′H, associated with delphinidin-derived flux, and of VcA3GT and VcBAHD, corresponding to reduced glycosylation and acylation. In Titan, compensatory regulation between VcF3′H and VcF3′5′H, suggesting pathway resilience. Correlation analysis suggested co-regulation within anthocyanin subclasses and inverse relationships between acylated and non-acylated forms. Overall, Titan displayed greater transcriptional and metabolic plasticity under thermal stress, highlighting temperature regulation of anthocyanins in blueberries. Our findings emphasize the need to select thermally resilient genotypes to cope with global warming scenarios.