Rapid Grapevine Health Diagnosis Based on Digital Imaging and Deep Learning.

Deep learning plays a vital role in precise grapevine disease detection, yet practical applications for farmer assistance are scarce despite promising results. The objective of this research is to develop an intelligent approach, supported by user-friendly, open-source software named AI GrapeCare (Version 1, created by Osama Elsherbiny). This approach utilizes RGB imagery and hybrid deep networks for the detection and prevention of grapevine diseases. Exploring the optimal deep learning architecture involved combining convolutional neural networks (CNNs), long short-term memory (LSTM), deep neural networks (DNNs), and transfer learning networks (including VGG16, VGG19, ResNet50, and ResNet101V2). A gray level co-occurrence matrix (GLCM) was employed to measure the textural characteristics. The plant disease detection platform (PDD) created a dataset of real-life grape leaf images from vineyards to improve plant disease identification. A data augmentation technique was applied to address the issue of limited images. Subsequently, the augmented dataset was used to train the models and enhance their capability to accurately identify and classify plant diseases in real-world scenarios. The analyzed outcomes indicated that the combined CNNRGB-LSTMGLCM deep network, based on the VGG16 pretrained network and data augmentation, outperformed the separate deep network and nonaugmented version features. Its validation accuracy, classification precision, recall, and F-measure are all 96.6%, with a 93.4% intersection over union and a loss of 0.123. Furthermore, the software developed through the proposed approach holds great promise as a rapid tool for diagnosing grapevine diseases in less than one minute. The framework of the study shows potential for future expansion to include various types of trees. This capability can assist farmers in early detection of tree diseases, enabling them to implement preventive measures.

An expertized grapevine disease image database including five grape varieties focused on Flavescence dorée and its confounding diseases, biotic and abiotic stresses.

The grapevine is vulnerable to diseases, deficiencies, and pests, leading to significant yield losses. Current disease controls involve monitoring and spraying phytosanitary products at the vineyard block scale. However, automatic detection of disease symptoms could reduce the use of these products and treat diseases before they spread. Flavescence dorée (FD), a highly infectious disease that causes significant yield losses, is only diagnosed by identifying symptoms on three grapevine organs: leaf, shoot, and bunch. Its diagnosis is carried out by scouting experts, as many other diseases and stresses, either biotic or abiotic, imply similar symptoms (but not all at the same time). These experts need a decision support tool to improve their scouting efficiency. To address this, a dataset of 1483 RGB images of grapevines affected by various diseases and stresses, including FD, was acquired by proximal sensing. The images were taken in the field at a distance of 1-2 meters to capture entire grapevines and an industrial flash was ensuring a constant luminance on the images regardless of the environmental circumstances. Images of 5 grape varieties (Cabernet sauvignon, Cabernet franc, Merlot, Ugni blanc and Sauvignon blanc) were acquired during 2 years (2020 and 2021). Two types of annotations were made: expert diagnosis at the grapevine scale in the field and symptom annotations at the leaf, shoot, and bunch levels on computer. On 744 images, the leaves were annotated and divided into three classes: 'FD symptomatic leaves', 'Esca symptomatic leaves', and 'Confounding leaves'. Symptomatic bunches and shoots were, in addition of leaves, annotated on 110 images using bounding boxes and broken lines, respectively. Additionally, 128 segmentation masks were created to allow the detection of the symptomatic shoots and bunches by segmentation algorithms and compare the results to those of the detection algorithms.

Evaluation of a decision support strategy for the control of powdery mildew, Erysiphe necator (Schw.) Burr., in grapevine in the central region of Chile.

BACKGROUND: The primary strategy to control powdery mildew in Chilean vineyards involves periodic fungicide spraying, which may lead to many environmental and human health risks. This study aimed to implement and evaluate the effectiveness and economic feasibility of a novel decision support strategy (DSS) to limit the number of treatments against this pathogen. An experiment was conducted between the 2010 and 2013 seasons in two irrigated vine fields, one containing a cultivar of Cabernet Sauvignon (CS) and the other a cultivar of Chardonnay (CH). RESULTS: The results showed that the DSS effectively controlled powdery mildew in CS and CH vine fields, as evidenced by a disease severity lower than 3%, which was lower than that observed in untreated vines (approximately 10 and 40% for CS and CH respectively). The DS strategy required the application of only 2-3 fungicide treatments per season in key vine phenological stages, and the cost fluctuated between $US 322 and 415 ha-1 , which was 40-60% cheaper than the traditional strategy employed by vine growers. CONCLUSION: The decision support strategy evaluated in this trial allows a good control of powdery mildew for various types of epidemic with an early and late initiation. © 2017 Society of Chemical Industry.

Hygienization and control of Diplodia seriata fungus in vine pruning waste composting and its seasonal variability in open and closed systems.

After the ban on sodium arsenite, waste management alternatives to the prevalent burning method, such as the hygienization and biodegradation in solid phase by composting, are required for the pruned material from grapevines affected by various fungi. In this work the dynamics of a fungus associated with vine decay (Diplodia seriata) during the composting process of a mixture of laying hen manure and vine pruning waste (2:1w/w) have been investigated in an open pile and a discontinuous closed biodigester. Through the optimization of the various physical-chemical parameters, hygienization of the infected waste materials was attained, yielding class-A organo-mineral fertilizers. Nevertheless, important differences in the efficiency of each system were observed: whereas in the open pile it took 10days to control D. seriata and 35 additional composting days to achieve full inactivation, in the discontinuous biodigester the fungus was entirely inactivated within the first 3-7days. Finally, the impact of seasonal variability was assessed and summer temperatures shown to have greater significance in the open pile.

Ecology and management of grapevine leafroll disease.

Grapevine leafroll disease (GLD) is caused by a complex of vector-borne virus species in the family Closteroviridae. GLD is present in all grape-growing regions of the world, primarily affecting wine grape varieties. The disease has emerged in the last two decades as one of the major factors affecting grape fruit quality, leading to research efforts aimed at reducing its economic impact. Most research has focused on the pathogens themselves, such as improved detection protocols, with limited work directed toward disease ecology and the development of management practices. Here we discuss the ecology and management of GLD, focusing primarily on Grapevine leafroll-associated virus 3, the most important virus species within the complex. We contextualize research done on this system within an ecological framework that forms the backbone of the discussion regarding current and potential GLD management strategies. To reach this goal, we introduce various aspects of GLD biology and ecology, followed by disease management case studies from four different countries and continents (South Africa, New Zealand, California-USA, and France). We review ongoing regional efforts that serve as models for improved strategies to control this economically important and worldwide disease, highlighting scientific gaps that must be filled for the development of knowledge-based sustainable GLD management practices.