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

Abstract

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. 

DOI:

Publication date: June 14, 2024

Issue: Open GPB 2024

Type: Poster

Authors

Prakriti Sharma1, Anne Fennell1*

1 South Dakota State University, Brookings SD, USA

Contact the author*

Keywords

Hyperspectral, photosynthesis, neural networks, rootstock

Tags

IVES Conference Series | Open GPB | Open GPB 2024

Citation

Related articles…

Terpenoids and norisoprenoids in italian red wines

AIM Terpene compounds are associated with floral notes and are characteristic of aromatic grape varieties such as Muscat (Jackson, 2008). They are generally considered to potentially contribute to the aroma of white wines. However, there is a growing interest towards the potential contribution of terpene compounds to the aroma of red wines. The aim of this work was to investigate the occurrence of different terpenes in red wines from Italian varieties. METHODS For this study wines from 11 mono-varietal Italian red wines from 12 regions were used (19 Sangiovese, 11 Nebbiolo, 10 Aglianico, 11 Primitivo, 10 Raboso del Piave, 9 Cannonau, 11 Teroldego, 3 Nerello, 9 Montepulciano, 7 Corvina). All samples were from vintage 2016 and none of them had been in contact with wood. A total of 19 terpenes and 7 norisoprenoids were analysed by mean of SPME-GC-MS analysis using a DVB-CAR-PDMS fiber. The wines were collected in the framework of the activities of the D-Wines (Diversity of Italian wines) project.

HPLC and SEC analysis on the flavonoids and the skin cell wall material of Merlot berries reveals new insights into the study of the phenolic maturity

Anthocyanins and tannins contribute to important sensorial traits of red wines, such as color and mouthfeel attributes.

Critical investigation on additions to improve the sensory characteristics of dealcoholized wine

The demand for dealcoholized wine has been progressively increasing in recent years. Moreover, the attention for such products is probably increasing even more. Due to that increasing demand and market awareness the legal authorities are about changing rules for that products. Also, at OIV level, these products are being intensively discussed for certain time. The production of dealcoholized wine bases on wine as initial product. This wine is then reduced by physical methods to an alcohol content of less than 0.5% vol., or in other words, to less than 4g/l of alcohol. There are various technologies are possible for producing dealcoholized wine (Schmitt and Christmann 2019).

The use of Hanseniaspora vineae on the production of base sparkling wine

Non-Saccharomyces yeasts have been associated, for many years, with challenging alcoholic fermentation processes. However, during the last decade the use of non-Saccharomyces yeasts in wine production has become increasingly widespread due to the advantages they can offer in mixed inoculations with Saccharomyces cerevisiae (Sc). In this respect, Hanseniaspora vineae (Hv), in synergy with Saccharomyces spp, represents an interesting opportunity to impart a positive contribution to the aroma complexity of wines. In fact, it is a well-known producer of pleasant esters, such as 2-phenylethyl acetate. This study compares the performances of Hv (strain Hv-205) in sequential inoculation modality to Sc in three Chardonnay musts for base sparkling wine production. No significant differences were observed in basic chemical parameters between wines except for titratable acidity, with a significantly decrease (up to 1.5 g/L) in Hv processes due to malic acid degradation. The analysis of the aroma compounds revealed remarkable differences in concentration of volatile metabolites, among others up to 37-fold increase of 2-phenylethyl acetate. In contrast, lower concentration of its alcohol were detected, suggesting higher acetylation activity by Hv.

Sensory study of potential kokumi compounds in wine 

Kokumi is a complex sensation perceived as enhanced palatability. Under the influence of kokumi substances, foods/beverages tastes become more flavorful with increased intensity, spread, continuity, richness, harmony, and punch which are the six related characteristics corresponding to the kokumi sensory concept (Yamamoto & Inui-Yamamoto 2023).