terclim by ICS banner
IVES 9 IVES Conference Series 9 Hyperspectral imaging and machine learning for monitoring grapevine physiology

Hyperspectral imaging and machine learning for monitoring grapevine physiology


Rootstocks are gaining importance in viticulture as a strategy to combat abiotic challenges, as well as enhancing scion physiology and attributes. Therefore, understanding how the rootstock affects photosynthesis is insightful for genetic improvement of either genotype in the grafted grapevines. Photosynthetic parameters such as maximum rate of carboxylation of RuBP (Vcmax) and the maximum rate of electron transport driving RuBP regeneration (Jmax) have been identified as ideal targets for breeding and genetic studies. However, techniques used to directly measure these photosynthetic parameters are limited to the single leaf level and are time-consuming measurements. Hyperspectral remote sensing uses the optical properties of the entire vine to predict photosynthetic capacity at the canopy level. In this study, estimates of Vcmax and Jmax were assessed, in six different rootstocks with a common scion, using direct measurements and canopy reflectance obtained with hyperspectral wavelengths (400 to 1000 nm). Using artificial intelligence-based modeling, prediction models were developed for Marquette on the six different rootstock genotypes. Results for direct and indirect measures indicate that each rootstock promotes differences in scion Vcmax and Jmaxprofiles across the season. Application of machine learning and neural networks of spectral data provided good predictions of both photosynthetic parameters. 


Publication date: June 14, 2024

Issue: Open GPB 2024

Type: Poster


Prakriti Sharma1, Anne Fennell1*

1 South Dakota State University, Brookings SD, USA

Contact the author*


Hyperspectral, photosynthesis, neural networks, rootstock


IVES Conference Series | Open GPB | Open GPB 2024


Related articles…

Differential gene expression and novel gene models in 110 Richter uncovered through RNA Sequencing of roots under stress

The appearance of the Phylloxera pest in the 19th century in Europe caused dramatical damages in grapevine diversity. To mitigate these losses, grapevine growers resorted to using crosses of different Vitis species, such as 110 Richter (110R) (V. berlandieri x V. rupestris), which has been invaluable for studying adaptations to stress responses in vineyards. Recently, a high quality chromosome scale assembly of 110R was released, but the available gene models were predicted without using as evidence transcriptional sequences obtained from roots, that are crucial organs in rootstock, and they may express certain genes exclusively. Therefore, we employed RNA sequencing reads of 110R roots under different stress conditions to predict new gene models in each haplotype of 110R under different stresses.

Caratterizzazione varietale della CV. Vranac del Montenegro: primi risultati

Questo studio ha permesso di raccogliere alcune informazioni sul profilo chimico della cultivar Vranac coltivata in Montenegro. L’uva ha mostrato di raggiungere un buon accumulo zuccherino

2018 updates on the agronomic performances of fungus resistant wine grapes in Trentino (Italy)

On the market there are several wine grapes which are tolerant to the main fungal diseases. These varieties, commonly defined “resistant”, were developed in the grapevine breeding programs carried out mainly in Germany, France, Hungary and Italy. Some of these cultivars have been included in the national catalogues of wine grape varieties and have sometimes been allowed for specific kinds of wine. The VEVIR project, aimed at the enological evaluation of resistant vines, involves 33 cultivars achieved at the State Institute for Viticulture Freiburg in Germany, the Research Institute of Viticulture and Enology Pecs in Hungary and the Fondazione Edmund Mach S. Michele all’Adige (FEM) in Italy.

Modelling grape and wine quality through PLS Spline statistical method

Started in 1994, this project intends to explain quality of grapes and wines using data of soil, climate and vineyard that are currently used in field trials.

Delaying grapevine budbreak and/or phenological stages

In the current climatic context, with milder winters leading to earlier budburst in most wine regions, vines are exposed to the risk of spring frosts for a longer period. Depending on the year, frost can lead to yield losses of between 20 and 100 %, jeopardizing the economic survival of wine estates. In addition, by destroying young shoots, spring frosts can impact the following season’s production, by reducing the number of canes available for pruning, for example. Late pruning is one method to combat spring frosts.