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…

Deficit irrigation and mechanical canopy management affect berry and wine phenolic and aroma composition of Syrah in Central California

Labor shortage is one of the most crucial issues in current viticulture. Mechanized approaches are helpful in reducing production costs and increasing vineyard efficiency but their effect on grapes and wines needs evaluation. This work assess the results of combined mechanical pruning and shoot thinning with deficit irrigation strategies to reduce management costs but not quality of production.

Preliminary characterisation of mannoproteins from different wine yeast strains and impact on wine properties

Mannoproteins (MPs) are released from the yeast cell wall during alcoholic fermentation and aging on the lees, and influence aspects of wine quality such as haze formation and colour stability. Yet, as this is a slow process with microbiological and sensory risks, the exogenous addition of extracted MPs poses an efficient alternative. While Saccharomyces cerevisiae has long been studied as a prominent source for MPs extraction, their structure and composition greatly differ between yeast species. This may influence their behaviour in the wine matrix and subsequent impact on wine properties. However, although wine yeast species other than S. cerevisiae possibly present an untapped source of MPs, they are still ill-characterised in terms of chemical composition and influence on wine.

Estudio de la adaptación y del comportamiento productivo y enológico de variedades blancas foráneas en la zona vitícola del Penedés

Estudio comparativo del comportamiento de ocho variedades de viníferas blancas en el Penedés, injertadas sobre los portainjertos 41-B y 110-R.
Se describen los comportamientos

Drought responses in Chardonnay and Sauvignon blanc grapevine cultivars: Mechanistic insights and varietal contrasts

This study explored the responses of Chardonnay and Sauvignon blanc grapevine cultivars to water deficit across four years, uncovering their shared patterns and distinctive coping mechanisms. The research was conducted in a commercial vineyard located in Isla de Maipo, Chile. Various characterization approaches were employed including plant water potentials (), gas exchange measurements, shoot vulnerability curves, productivity assessments, and leaf cell water relations. Linear mixed models and sensitivity analyses were performed using various statistical methods to evaluate cultivar responses to water deficit. As the water deficit progressed, both cultivars displayed a parallel reduction in stomatal conductance, leaf turgor, and increased shoot embolism.

Merging fast sensory profiling with non-targeted GC-MS analysis for multifactorial experimental wine making

Wine aroma is influenced by several viticultural and oenological factors. In this study we used experimental wine making in a full factorial design to determine the impact of grapevine age, must turbidity, and yeast strain on the aroma of Vitis vinifera L. cv. Riesling wines. A recently developed, non-targeted SPME-GC-MS fingerprinting approach for wine volatiles was used. This approach includes the segmentation and mathematical transformation of chromatograms in combination with Parallel Factor Analysis (PARAFAC) and subsequent deconvolution of important chromatogram segments.