Phenotyping grapevine red blotch virus and grapevine leafroll-associated viruses before and after symptom expression through machine-learning analysis of hyperspectral images

Abstract

IntroductionGrapevine leafroll-associated viruses (GLRaVs) and grapevine red blotch virus (GRBV) cause substantial economic losses and concern to North America’s grape and wine industries. Fast and accurate identification of these two groups of viruses is key to informing disease management strategies and limiting their spread by insect vectors in the vineyard. Hyperspectral imaging offers new opportunities for virus disease scouting.MethodsHere we used two machine learning methods, i.e., Random Forest (RF) and 3D-Convolutional Neural Network (CNN), to identify and distinguish leaves from red blotch-infected vines, leafroll-infected vines, and vines co-infected with both viruses using spatiospectral information in the visible domain (510-710nm). We captured hyperspectral images of about 500 leaves from 250 vines at two sampling times during the growing season (a pre-symptomatic stage at veraison and a symptomatic stage at mid-ripening). Concurrently, viral infections were determined in leaf petioles by polymerase chain reaction (PCR) based assays using virus-specific primers and by visual assessment of disease symptoms.ResultsWhen binarily classifying infected vs. non-infected leaves, the CNN model reaches an overall maximum accuracy of 87% versus 82.8% for the RF model. Using the symptomatic dataset lowers the rate of false negatives. Based on a multiclass categorization of leaves, the CNN and RF models had a maximum accuracy of 77.7% and 76.9% (averaged across both healthy and infected leaf categories). Both CNN and RF outperformed visual assessment of symptoms by experts when using RGB segmented images. Interpretation of the RF data showed that the most important wavelengths were in the green, orange, and red subregions.DiscussionWhile differentiation between plants co-infected with GLRaVs and GRBV proved to be relatively challenging, both models showed promising accuracies across infection categories.

Hyper Spectral Imaging and Optimized Neural Networks for Early Detection of Grapevine Viral Disease

“…While differentiating co-infected plants was more difficult, both models demonstrated good results across all infection categories. In study [21] four machine learning algorithms were used. In 10-fold cross-validation, the boosted regression tree (BRT) model with SPA-selected wavelengths produced the best results, with 85.2% accuracy and an AUC of 0.932.…”

Field-Deployed Spectroscopy from 350 to 2500 nm: A Promising Technique for Early Identification of Powdery Mildew Disease (Erysiphe necator) in Vineyards

“…Crop diseases and pests significantly impact global agricultural production, quality, and economic outcomes [1]. In the field of viticulture, several diseases significantly impact grapevine health, such as grapevine trunk diseases like Esca [2], Grapevine Red Blotch Disease and Grapevine Leafroll Disease [3] or Botrytis, which leads to botrytis bunch rot or grey mould [4]. Each disease presents unique challenges, requiring specific management and control strategies.…”

Assessing the capacity of high-resolution commercial satellite imagery for grapevine downy mildew detection and surveillance in New York state

“…However, most prior work on grapevine remote sensing has aimed to detect water stress, with few studies addressing other abiotic parameters such as nitrogen content, yield, and fruit composition (Giovos et al 2021). Reports on proximal and remote sensing of grapevine diseases are dominated by near-surface platforms and increasingly by hyperspectral cameras (both proximal and airborne) (Naidu et al 2009; Oerke, Herzog, and Toepfer 2016; MacDonald et al 2016; Bendel et al 2020; Gao et al 2020; Lacotte et al 2022; Sawyer et al 2023; di Gennaro et al 2016; Matese et al 2022; Cséfalvay et al 2009; Galvan et al 2023). Most studies aim to detect disease at a single point in time, while season-long, operational surveillance systems remain largely unexplored.…”