Grapevine red blotch virus detection in the vineyard: Leveraging machine learning with VIS/NIR hyperspectral images for asymptomatic and symptomatic vines
Computers and Electronics in Agriculture · 2025-07 · 234 · 110251
DOI: 10.1016/j.compag.2025.110251 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers and Electronics in Agriculture, 2025-07. Verfasst von E. Laroche-Pinel und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: California Department of Food and Agriculture, California State University Agricultural Research Institute.
Abstract (Originalsprache)
• Grapevine Red Blotch Virus (GRBV) is a substantial threat to the grapevine industry. • Identification and removal of infected vines (roguing) are critical to reduce spread. • Scouting can be automatized with hyperspectral imaging and machine-learning. • Results on hyperspectral scouting are comparable to expert-assessment in the field. • We explored simplifying the sensing method to develop sensors for growers. A decade after the discovery of grapevine red blotch virus (GRBV), there is ample evidence of its detrimental impacts on grapevine physiology, grape composition, and wine production. To mitigate the spread of GRBV in vineyards, roguing is recommended as a disease management response. The imperative to identify and remove diseased vines justifies the development of autonomous scouting. In this study, nearly 700 ground-based hyperspectral images, encompassing both symptomatic and asymptomatic vine canopies, were collected in a Cabernet Franc vineyard during two growing seasons, capturing pre- and post-veraison vine development stages. Spanning 230 bands from visible (VIS) to near-infrared (NIR) domains (510 to 900 nm with 1.7 nm width), canopy spectral signals were isolated from the background through semantic segmentation using U-Net. Simultaneously, the GRBV status of each vine was established in the laboratory through polymerase chain reaction. These two intertwined datasets were used for training various machine learning algorithms and their ensembles. In addition, strategies to reduce dataset size through spectral binning and testing three different feature selection methods (Recursive Feature Elimination, Univariate Feature Selection, and taking into consideration autocorrelation) were explored. Our findings revealed that hyperspectral imagery identified GRBV-infected vines with an accuracy of 75.7 % around harvest, coinciding with the peak of disease symptom expression, utilizing only 19 bands with a 16 nm bin width. Prior to veraison when most vines are asymptomatic, an accuracy of 74.2 % was achieved, employing 5 bands with a 16 nm bin width. This study substantiates the utility of hyperspectral images in the identification of GRBV-infected vines, offering a robust foundation for the development of a streamlined sensing system that holds great promise for the grape and wine industry in effectively scouting vineyards for GRBV.
Förderung
- California Department of Food and Agriculture
- California State University Agricultural Research Institute
Zitieren
APA
Laroche-Pinel, E., Singh, K., Flasco, M., Cooper, M., Fuchs, M., & Brillante, L. (2025). Grapevine red blotch virus detection in the vineyard: Leveraging machine learning with VIS/NIR hyperspectral images for asymptomatic and symptomatic vines. Computers and Electronics in Agriculture, 234, 110251. https://doi.org/10.1016/j.compag.2025.110251
Vancouver
Laroche-Pinel E, Singh K, Flasco M, Cooper M, Fuchs M, Brillante L. Grapevine red blotch virus detection in the vineyard: Leveraging machine learning with VIS/NIR hyperspectral images for asymptomatic and symptomatic vines. Computers and Electronics in Agriculture. 2025;234:110251. doi:10.1016/j.compag.2025.110251
BibTeX
@article{LarochePinel2025,
author = {Laroche-Pinel, E. and Singh, K. and Flasco, M. and Cooper, M.L. and Fuchs, M. and Brillante, L.},
title = {Grapevine red blotch virus detection in the vineyard: Leveraging machine learning with VIS/NIR hyperspectral images for asymptomatic and symptomatic vines},
journal = {Computers and Electronics in Agriculture},
year = {2025},
volume = {234},
pages = {110251},
doi = {10.1016/j.compag.2025.110251}
}
EUVIMED