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…

Reaction Mechanisms of Copper and Iron with Hydrogen Sulfide and Thiols in Model Wine

Fermentation derived sulfidic off-odors due to hydrogen sulfide (H2S) and low molecular weight thiols are commonly encountered in wine production and removed by Cu(II) fining. However, the mechanism underlying Cu(II) fining remains poorly understood, and generally results in increased Cu concentration that lead to deleterious reactions in finished wine. The present study describes a mechanistic investigation of the iron and copper mediated reaction of H2S, cysteine, 3-sulfanylhexan-1-ol, and 6-sulfanylhexan-1-ol with oxygen. The concentrations of H2S, thiols, oxygen, and acetaldehyde were monitored over time. It was found that Cu(II) was rapidly reduced by both H2S and thiols to Cu(I).

The wine: a never-ending source of H2S and methanethiol

Volatile sulfur compounds (VSCs), mainly hydrogen sulfide and methanethiol (H2S and MeSH), are the responsible for reductive off-odor in wine.

Integrative grape to wine metabolite analyses to study the vineyard “memory” of wine

Wine production is a complex multi-step process and the end-product is not easily defined in terms of composition and quality due to the diversity of the raw materials (grapes) and the biological agents (yeast and bacteria) used/present during the fermentation. Furthermore, linking what happens in the vineyard to the wine fermentation and ultimately to characteristics in the wine during ageing

Removal of Fumonisin B1 and B2 from red wine using polymeric substances

The Ability of PVPP (Polyvinylpolypyrrolidone), PVP-DEGMA-TAIC (copolimerization of N-vinyl-2-pyrrolidinone with ethylene glycol dimethacrylate and triallyl isocyanurate) and PAEGDMA
(poly(acrylamide-co-ethylene glycol dimethacrylate)) polymers was tested as removal agents for Fumonisin B1 (FB1) and Fumonisin B2 (FB2) from model solutions and red wine. The polymers removal capacity was checked at three different resident times (2, 8 and 24 hours of contact time between the polymer and the sample), showing no differences in the percentage of FB1 and FB2 removal. Then, different polymer concentrations (1, 5 and 10 mg mL-1) were tested in model solution with and without phenolics (i.e. gallic acid and 4-methylcatechol).

Rootstock influence on xylem embolized vulnerability and scion behavior under severe water deficit

Severe water stress events can induce cavitation damage by xylem embolism in grapevine, diminishing plant hydraulic conductance. This work aimed to determine the rootstock effects on 1) xylem embolism vulnerability to understand its function failure under severe drought, including segmentation processes from leaf to root; and 2) hydraulic conductance across water deficit and its recovery. For this purpose, two complementary experiments were performed in one-year-old Vitis vinifera cv. Tempranillo grafted onto two different rootstocks (110-Richter and SO4) under well-watered 12L pot conditions. In experiment 1, the water-stress induced xylem embolism was monitored in leaves and stems, above and below grafting-point, by using “Cavicam” for determining the percentage of embolized vessels (at P12, P50 and P88).