Plant Disease Sensing: Studying Plant-Pathogen Interactions at Scale

Non-Destructive Monitoring of Foliar Fungicide Efficacy with Hyperspectral Sensing in Grapevine

Frequent fungicide applications are required to manage grapevine powdery mildew (Erysiphe necator). However, this practice is costly and has led to widespread fungicide resistance. A method of monitoring in-field fungicide efficacy could help growers maximize spray-interval length, thereby reducing costs and the rate of fungicide resistance emergence. The goal of this study was to evaluate if hyperspectral sensing in the visible to shortwave infrared range (400 to 2,400 nm) can quantify foliar fungicide efficacy on grape leaves. Commercial formulations of metrafenone, Bacillus mycoides isolate J (BmJ), and sulfur were applied on Chardonnay grapevines in vineyard or greenhouse settings. Foliar reflectance was measured with handheld hyperspectral spectroradiometers at multiple days post-application. Fungicide efficacy was estimated as a proxy for fungicide residue and disease control measured with the Blackbird microscopy imaging robot. Treatments could be differentiated from the untreated control with an accuracy of 73.06% for metrafenone, 67.76% for BmJ, and 94.10% for sulfur. The change in spectral reflectance was moderately correlated with the cube root of the area under the disease progress curve for metrafenone- and sulfur-treated samples (R2 = 0.38 and 0.36, respectively) and with sulfur residue (R2 = 0.42). BmJ treatment impacted foliar physiology by enhancing the leaf mass/area and reducing the nitrogen and total phenolic content as estimated from spectral reflectance. The results suggest that hyperspectral sensing can be used to monitor in-situ fungicide efficacy, and the prediction accuracy depends on the fungicide and the time point measured. The ability to monitor in-situ fungicide efficacy could facilitate more strategic fungicide applications and promote sustainable grapevine protection. [Formula: see text] Copyright © 2024 The Author(s). This is an open access article distributed under the CC BY-NC-ND 4.0 International license.

MS-Net: a novel lightweight and precise model for plant disease identification

The rapid development of image processing technology and the improvement of computing power in recent years have made deep learning one of the main methods for plant disease identification. Currently, many neural network models have shown better performance in plant disease identification. Typically, the performance improvement of the model needs to be achieved by increasing the depth of the network. However, this also increases the computational complexity, memory requirements, and training time, which will be detrimental to the deployment of the model on mobile devices. To address this problem, a novel lightweight convolutional neural network has been proposed for plant disease detection. Skip connections are introduced into the conventional MobileNetV3 network to enrich the input features of the deep network, and the feature fusion weight parameters in the skip connections are optimized using an improved whale optimization algorithm to achieve higher classification accuracy. In addition, the bias loss substitutes the conventional cross-entropy loss to reduce the interference caused by redundant data during the learning process. The proposed model is pre-trained on the plant classification task dataset instead of using the classical ImageNet for pre-training, which further enhances the performance and robustness of the model. The constructed network achieved high performance with fewer parameters, reaching an accuracy of 99.8% on the PlantVillage dataset. Encouragingly, it also achieved a prediction accuracy of 97.8% on an apple leaf disease dataset with a complex outdoor background. The experimental results show that compared with existing advanced plant disease diagnosis models, the proposed model has fewer parameters, higher recognition accuracy, and lower complexity.

A Rapid Glove-Based Inoculum Sampling Technique to Monitor Erysiphe necator in Commercial Vineyards

Information on the presence and severity of grape powdery mildew (GPM), caused by Erysiphe necator, has long been used to guide management decisions. While recent advances in the available molecular diagnostic assays and particle samplers have made monitoring easier, there is still a need for more efficient field collection of E. necator. The use of vineyard worker gloves worn during canopy manipulation as a sampler (glove swab) of E. necator was compared with samples identified by visual assessment with subsequent molecular confirmation (leaf swabs) and airborne spore samples collected by rotating-arm impaction traps (impaction traps). Samples from United States commercial vineyards in Oregon, Washington, and California were analyzed using two TaqMan qPCR assays targeting the internal transcribed spacer regions or cytochrome b gene of E. necator. Based on qPCR assays, visual disease assessments misidentified GPM up to 59% of the time with a higher frequency of misidentification occurring earlier in the growing season. Comparison of the aggregated leaf swab results for a row (n = 915) to the row's corresponding glove swab had 60% agreement. The latent class analysis (LCA) indicated that glove swabs were more sensitive than leaf swabs in detecting E. necator presence. The impaction trap results had 77% agreement to glove swabs (n = 206) taken from the same blocks. The LCAs estimated that the glove swabs and impaction trap samplers varied each year in which was more sensitive for detection. This likely indicates that these methods have similar levels of uncertainty and provide equivalent information. Additionally, all samplers, once E. necator was detected, were similarly sensitive and specific for detection of the A-143 resistance allele. Together, these results suggest that glove swabs are an effective sampling method for monitoring the presence of E. necator and, subsequently, the G143A amino acid substitution associated with resistance to quinone outside inhibitor fungicides in vineyards. Glove swabs could reduce sampling costs due to the lack of need for specialized equipment and time required for swab collection and processing.

Soil and Phytomicrobiome for Plant Disease Suppression and Management under Climate Change: A Review

The phytomicrobiome plays a crucial role in soil and ecosystem health, encompassing both beneficial members providing critical ecosystem goods and services and pathogens threatening food safety and security. The potential benefits of harnessing the power of the phytomicrobiome for plant disease suppression and management are indisputable and of interest in agriculture but also in forestry and landscaping. Indeed, plant diseases can be mitigated by in situ manipulations of resident microorganisms through agronomic practices (such as minimum tillage, crop rotation, cover cropping, organic mulching, etc.) as well as by applying microbial inoculants. However, numerous challenges, such as the lack of standardized methods for microbiome analysis and the difficulty in translating research findings into practical applications are at stake. Moreover, climate change is affecting the distribution, abundance, and virulence of many plant pathogens, while also altering the phytomicrobiome functioning, further compounding disease management strategies. Here, we will first review literature demonstrating how agricultural practices have been found effective in promoting soil health and enhancing disease suppressiveness and mitigation through a shift of the phytomicrobiome. Challenges and barriers to the identification and use of the phytomicrobiome for plant disease management will then be discussed before focusing on the potential impacts of climate change on the phytomicrobiome functioning and disease outcome.

Early detection of late blight in potato by whole-plant redox imaging

Late blight caused by the oomycete Phytophthora infestans is a most devastating disease of potatoes (Solanum tuberosum). Its early detection is crucial for suppressing disease spread. Necrotic lesions are normally seen in leaves at 4 days post-inoculation (dpi) when colonized cells are dead, but early detection of the initial biotrophic growth stage, when the pathogen feeds on living cells, is challenging. Here, the biotrophic growth phase of P. infestans was detected by whole-plant redox imaging of potato plants expressing chloroplast-targeted reduction-oxidation sensitive green fluorescent protein (chl-roGFP2). Clear spots on potato leaves with a lower chl-roGFP2 oxidation state were detected as early as 2 dpi, before any visual symptoms were recorded. These spots were particularly evident during light-to-dark transitions, and reflected the mislocalization of chl-roGFP2 outside the chloroplasts. Image analysis based on machine learning enabled systematic identification and quantification of spots, and unbiased classification of infected and uninfected leaves in inoculated plants. Comparing redox with chlorophyll fluorescence imaging showed that infected leaf areas that exhibit mislocalized chl-roGFP2 also showed reduced non-photochemical quenching and enhanced quantum PSII yield (ΦPSII) compared with the surrounding leaf areas. The data suggest that mislocalization of chloroplast-targeted proteins is an efficient marker of late blight infection, and demonstrate how it can be utilized for non-destructive monitoring of the disease biotrophic stage using whole-plant redox imaging.

In-field hyperspectral imaging dataset of Manzanilla and Gordal olive varieties throughout the season

Because spectral technology has exhibited benefits in food-related applications, an increasing amount of effort is being dedicated to develop new food-related spectral technologies. In recent years, the use of remote sensing or unmanned aerial vehicles for precision agriculture has increased. As spectral technology continues to improve, portable spectral devices become available in the market, offering the possibility of realising in-field monitoring. This study demonstrates hyperspectral imaging and spectral olive signatures of the Manzanilla and Gordal cultivars analysed throughout the table-olive season from May to September. The data were acquired using an in-field technique and sampled via a non-destructive approach. The olives were monitored periodically during the season using a hyperspectral camera. A white reference was used to normalise the illumination variability in the spectra. The acquired data were saved in files named raw, normalised, and processed data. The normalised data were calculated by the sensor by correcting the white and black levels using the acquired reflectance values. The olive spectral signature of the images is saved in the processed data files. The images were labelled and processed using an algorithm to retrieve the olive spectral signatures. The results were stored as a chart with 204 columns and 'n' rows. Each row represents the pixel of an olive in the image, and the columns contain the reflectance information at that specific band. These data provide information about two olive cultivars during the season, which can be used for various research purposes. Statistical and artificial intelligence approaches correlate spectral signatures with olive characteristics such as growth level, organoleptic properties, or even cultivar classification.

Deep semantic segmentation for the quantification of grape foliar diseases in the vineyard

Plant disease evaluation is crucial to pathogen management and plant breeding. Human field scouting has been widely used to monitor disease progress and provide qualitative and quantitative evaluation, which is costly, laborious, subjective, and often imprecise. To improve disease evaluation accuracy, throughput, and objectiveness, an image-based approach with a deep learning-based analysis pipeline was developed to calculate infection severity of grape foliar diseases. The image-based approach used a ground imaging system for field data acquisition, consisting of a custom stereo camera with strobe light for consistent illumination and real time kinematic (RTK) GPS for accurate localization. The deep learning-based pipeline used the hierarchical multiscale attention semantic segmentation (HMASS) model for disease infection segmentation, color filtering for grapevine canopy segmentation, and depth and location information for effective region masking. The resultant infection, canopy, and effective region masks were used to calculate the severity rate of disease infections in an image sequence collected in a given unit (e.g., grapevine panel). Fungicide trials for grape downy mildew (DM) and powdery mildew (PM) were used as case studies to evaluate the developed approach and pipeline. Experimental results showed that the HMASS model achieved acceptable to good segmentation accuracy of DM (mIoU > 0.84) and PM (mIoU > 0.74) infections in testing images, demonstrating the model capability for symptomatic disease segmentation. With the consistent image quality and multimodal metadata provided by the imaging system, the color filter and overlapping region removal could accurately and reliably segment grapevine canopies and identify repeatedly imaged regions between consecutive image frames, leading to critical information for infection severity calculation. Image-derived severity rates were highly correlated (r > 0.95) with human-assessed values, and had comparable statistical power in differentiating fungicide treatment efficacy in both case studies. Therefore, the developed approach and pipeline can be used as an effective and efficient tool to quantify the severity of foliar disease infections, enabling objective, high-throughput disease evaluation for fungicide trial evaluation, genetic mapping, and breeding programs.

Climate Change Effects on Pathogen Emergence: Artificial Intelligence to Translate Big Data for Mitigation

Plant pathology has developed a wide range of concepts and tools for improving plant disease management, including models for understanding and responding to new risks from climate change. Most of these tools can be improved using new advances in artificial intelligence (AI), such as machine learning to integrate massive data sets in predictive models. There is the potential to develop automated analyses of risk that alert decision-makers, from farm managers to national plant protection organizations, to the likely need for action and provide decision support for targeting responses. We review machine-learning applications in plant pathology and synthesize ideas for the next steps to make the most of these tools in digital agriculture. Global projects, such as the proposed global surveillance system for plant disease, will be strengthened by the integration of the wide range of new data, including data from tools like remote sensors, that are used to evaluate the risk ofplant disease. There is exciting potential for the use of AI to strengthen global capacity building as well, from image analysis for disease diagnostics and associated management recommendations on farmers' phones to future training methodologies for plant pathologists that are customized in real-time for management needs in response to the current risks. International cooperation in integrating data and models will help develop the most effective responses to new challenges from climate change.