Optical detection of downy mildew in grapevine leaves: daily kinetics of autofluorescence upon infection

Stress phenotyping analysis leveraging autofluorescence image sequences with machine learning

Background

Autofluorescence-based imaging has the potential to non-destructively characterize the biochemical and physiological properties of plants regulated by genotypes using optical properties of the tissue. A comparative study of stress tolerant and stress susceptible genotypes of Brassica rapa with respect to newly introduced stress-based phenotypes using machine learning techniques will contribute to the significant advancement of autofluorescence-based plant phenotyping research.

Methods

Autofluorescence spectral images have been used to design a stress detection classifier with two classes, stressed and non-stressed, using machine learning algorithms. The benchmark dataset consisted of time-series image sequences from three Brassica rapa genotypes (CC, R500, and VT), extreme in their morphological and physiological traits captured at the high-throughput plant phenotyping facility at the University of Nebraska-Lincoln, USA. We developed a set of machine learning-based classification models to detect the percentage of stressed tissue derived from plant images and identified the best classifier. From the analysis of the autofluorescence images, two novel stress-based image phenotypes were computed to determine the temporal variation in stressed tissue under progressive drought across different genotypes, i.e., the average percentage stress and the moving average percentage stress.

Results

The study demonstrated that both the computed phenotypes consistently discriminated against stressed versus non-stressed tissue, with oilseed type (R500) being less prone to drought stress relative to the other two Brassica rapa genotypes (CC and VT).

Conclusion

Autofluorescence signals from the 365/400 nm excitation/emission combination were able to segregate genotypic variation during a progressive drought treatment under a controlled greenhouse environment, allowing for the exploration of other meaningful phenotypes using autofluorescence image sequences with significance in the context of plant science.

Hyperspectral mapping of the response of grapevine cultivars to Plasmopara viticola infection at the tissue scale

Resistance of grapevine to Plasmopara viticola is associated with the hypersensitive reaction, accumulation of stilbenoids, and formation of callose depositions. Spectral characterization of infected leaf tissue of cvs 'Regent' and 'Solaris' with resistance genes Rpv 3-1 and Rpv 10 and Rpv 3-3, respectively, suggested that resistance is not dependent on large-scale necrotization of host tissue. Reactions of the resistant cultivars and a reference susceptible to P. viticola were studied using hyperspectral imaging (range 400-1000 nm) at the tissue level and microscopic techniques. Resistance of both cultivars was incomplete and allowed pathogen reproduction. Spectral vegetation indices characterized the host response to pathogen invasion; the vitality of infected and necrotic leaf tissue differed significantly. Resistance depended on local accumulation of polyphenols in response to haustorium formation and was more effective for cv. 'Solaris'. Although hypersensitive reaction of some cells prevented colonization of palisade parenchyma, resistance was not associated with extensive necrotization of tissue, and the biotrophic pathogen survived localized death of penetrated host cells. Hyperspectral imaging was suitable to characterize and differentiate the resistance reactions of grapevine cultivars by mapping of the cellular response to pathogen attack on the tissue level and yields useful information on host-pathogen interactions.

Spatial-Spectral Analysis of Hyperspectral Images Reveals Early Detection of Downy Mildew on Grapevine Leaves

Downy mildew is a highly destructive disease of grapevine. Currently, monitoring for its symptoms is time-consuming and requires specialist staff. Therefore, an automated non-destructive method to detect the pathogen before the visible symptoms appear would be beneficial for early targeted treatments. The aim of this study was to detect the disease early in a controlled environment, and to monitor the disease severity evolution in time and space. We used a hyperspectral image database following the development from 0 to 9 days post inoculation (dpi) of three strains of Plasmopara viticola inoculated on grapevine leaves and developed an automatic detection tool based on a Support Vector Machine (SVM) classifier. The SVM obtained promising validation average accuracy scores of 0.96, a test accuracy score of 0.99, and it did not output false positives on the control leaves and detected downy mildew at 2 dpi, 2 days before the clear onset of visual symptoms at 4 dpi. Moreover, the disease area detected over time was higher than that when visually assessed, providing a better evaluation of disease severity. To our knowledge, this is the first study using hyperspectral imaging to automatically detect and show the spatial distribution of downy mildew on grapevine leaves early over time.

Identification and Classification of Downy Mildew Severity Stages in Watermelon Utilizing Aerial and Ground Remote Sensing and Machine Learning

Remote sensing and machine learning (ML) could assist and support growers, stakeholders, and plant pathologists determine plant diseases resulting from viral, bacterial, and fungal infections. Spectral vegetation indices (VIs) have shown to be helpful for the indirect detection of plant diseases. The purpose of this study was to utilize ML models and identify VIs for the detection of downy mildew (DM) disease in watermelon in several disease severity (DS) stages, including low, medium (levels 1 and 2), high, and very high. Hyperspectral images of leaves were collected in the laboratory by a benchtop system (380-1,000 nm) and in the field by a UAV-based imaging system (380-1,000 nm). Two classification methods, multilayer perceptron (MLP) and decision tree (DT), were implemented to distinguish between healthy and DM-affected plants. The best classification rates were recorded by the MLP method; however, only 62.3% accuracy was observed at low disease severity. The classification accuracy increased when the disease severity increased (e.g., 86-90% for the laboratory analysis and 69-91% for the field analysis). The best wavelengths to differentiate between the DS stages were selected in the band of 531 nm, and 700-900 nm. The most significant VIs for DS detection were the chlorophyll green (Cl green), photochemical reflectance index (PRI), normalized phaeophytinization index (NPQI) for laboratory analysis, and the ratio analysis of reflectance spectral chlorophyll-a, b, and c (RARSa, RASRb, and RARSc) and the Cl green in the field analysis. Spectral VIs and ML could enhance disease detection and monitoring for precision agriculture applications.

Remote Sensing of Diseases

Detection, identification, and quantification of plant diseases by sensor techniques are expected to enable a more precise disease control, as sensors are sensitive, objective, and highly available for disease assessment. Recent progress in sensor technology and data processing is very promising; nevertheless, technical constraints and issues inherent to variability in host-pathogen interactions currently limit the use of sensors in various fields of application. The information from spectral [e.g., RGB (red, green, blue)], multispectral, and hyperspectral sensors that measure reflectance, fluorescence, and emission of radiation or from electronic noses that detect volatile organic compounds released from plants or pathogens, as well as the potential of sensors to characterize the health status of crops, is evaluated based on the recent literature. Phytopathological aspects of remote sensing of plant diseases across different scales and for various purposes are discussed, including spatial disease patterns, epidemic spread of pathogens, crop characteristics, and links to disease control. Future challenges in sensor use are identified.

Leaf position-dependent effect of Alternaria brassicicola development on host cell death, photosynthesis and secondary metabolites in Brassica juncea

During the first 24 hours of infection, Alternaria brassicicola developmental parameters such as conidial germination, germ tubes and appressoria formation on each of the five mature Brassica juncea leaves, correlated with a leaf position showing stronger development of the pathogen on older leaves than on young ones. As a consequence of fungal development, the black spot disease was observed during 96 hours of infection on a macroscopic scale, as well as via confocal microscopy. Degradation of the chloroplast thylakoids and plastoglobule appearance during infection, followed by the decrease in chlorophyll a fluorescence parameters i.e. maximum quantum yield of PSII (F_v /F_m ), non-photochemical quenching (NPQ) and chlorophyll a:b ratio, have been observed. Also, after an initial increase of carbohydrates (glucose, fructose and sucrose), content far below the respective control values was found. The content of secondary metabolites such as flavonoids and glucosinolates increased in a leaf position-dependent manner in infected leaves, with a lower level in older leaves than in younger ones. Although, the total phenolic compounds (TPCs) content did not differ significantly in infected leaves compared to control leaves, TPCs level in both control and infected leaves was leaf position-dependent. To the best of our knowledge, this is the first report on leaf position-dependent effect on the B. juncea biochemical response to A. brassicicola infection.

Predicting Key Agronomic Soil Properties with UV-Vis Fluorescence Measurements Combined with Vis-NIR-SWIR Reflectance Spectroscopy: A Farm-Scale Study in a Mediterranean Viticultural Agroecosystem

For adequate crop and soil management, rapid and accurate techniques for monitoring soil properties are particularly important when a farmer starts up his activities and needs a diagnosis of his cultivated fields. This study aimed to evaluate the potential of fluorescence measured directly on 146 whole soil solid samples, for predicting key soil properties at the scale of a 6 ha Mediterranean wine estate with contrasting soils. UV-Vis fluorescence measurements were carried out in conjunction with reflectance measurements in the Vis-NIR-SWIR range. Combining PLSR predictions from Vis-NIR-SWIR reflectance spectra and from a set of fluorescence signals enabled us to improve the power of prediction of a number of key agronomic soil properties including SOC, N_tot, CaCO₃, iron, fine particle-sizes (clay, fine silt, fine sand), CEC, pH and exchangeable Ca²⁺ with cross-validation RPD ≥ 2 and R² ≥ 0.75, while exchangeable K⁺, Na⁺, Mg²⁺, coarse silt and coarse sand contents were fairly predicted (1.42 ≤ RPD < 2 and 0.54 ≤ R² < 0.75). Predictions of SOC, N_tot, CaCO₃, iron contents, and pH were still good (RPD ≥ 1.8, R² ≥ 0.68) when using a single fluorescence signal or index such as SFR_R or FERARI, highlighting the unexpected importance of red excitations and indices derived from plant studies. The predictive ability of single fluorescence indices or original signals was very significant for topsoil: this is very important for a farmer who wishes to update information on soil nutrient for the purpose of fertility diagnosis and particularly nitrogen fertilization. These results open encouraging perspectives for using miniaturized fluorescence devices enabling red excitation coupled with red or far-red fluorescence emissions directly in the field.

Correlative Analysis of Fluorescent Phytoalexins by Mass Spectrometry Imaging and Fluorescence Microscopy in Grapevine Leaves

Plant response to their environment stresses is a complex mechanism involving secondary metabolites. Stilbene phytoalexins, namely resveratrol, pterostilbene, piceids and viniferins play a key role in grapevine (Vitis vinifera) leaf defense. Despite their well-established qualities, conventional analyses such as HPLC-DAD or LC-MS lose valuable information on metabolite localization during the extraction process. To overcome this issue, a correlative analysis combining mass spectroscopy imaging (MSI) and fluorescence imaging was developed to localize in situ stilbenes on the same stressed grapevine leaves. High-resolution images of the stilbene fluorescence provided by macroscopy were supplemented by specific distributions and structural information concerning resveratrol, pterostilbene, and piceids obtained by MSI. The two imaging techniques led to consistent and complementary data on the stilbene spatial distribution for the two stresses addressed: UV-C irradiation and infection by Plasmopara viticola. Results emphasize that grapevine leaves react differently depending on the stress. A rather uniform synthesis of stilbenes is induced after UV-C irradiation, whereas a more localized synthesis of stilbenes in stomata guard cells and cell walls is induced by P. viticola infection. Finally, this combined imaging approach could be extended to map phytoalexins of various plant tissues with resolution approaching the cellular level.

Hyperspectral phenotyping of the reaction of grapevine genotypes to Plasmopara viticola

A major aim in grapevine breeding is the provision of cultivars resistant to downy mildew. As Plasmopara viticola produces sporangia on the abaxial surface of susceptible cultivars, disease symptoms on both leaf sides may be detected and quantified by technical sensors. The response of cultivars 'Mueller-Thurgau', 'Regent', and 'Solaris', which differ in resistance to P. viticola, was characterized under controlled conditions by using hyperspectral sensors. Spectral reflectance was suitable to differentiate between non-infected cultivars and leaf sides of the bicolored grapevine. Brown discoloration of tissue became visible on both leaf sides of resistant cultivars 2 days before downy mildew symptoms appeared on the susceptible 'Mueller-Thurgau' cultivar. Infection of this cultivar resulted in significant (P<0.05) reflectance changes 1-2 days prior to abaxial sporulation induced by high relative humidity, or the formation of adaxial oil spots. Hyperspectral imaging was more sensitive in disease detection than non-imaging and provided spatial information on the leaf level. Spectral indices provided information on the variability of chlorophyll content, photosynthetic activity, and relative water content of leaf tissue in time and space. On 'Mueller-Thurgau' downy mildew translated reflectance to higher values as detectable by the index DMI_3=(R₄₇₀+R₆₈₂+R₈₀₀)/(R₈₀₀/R₆₈₂) and affected reflectance at 1450nm. Tissue discoloration on 'Regent' and 'Solaris' cultivars was associated with lower reflectance between 750 and 900nm; blue and red reflectance demonstrated differences from leaf necroses. With high inoculum densities, P. viticola sporulated on even resistant cultivars. Hyperspectral characterization at the tissue level proved suitable for phenotyping plant resistance to pathogens and provided information on resistance mechanisms.

First detection of the presence of naturally occurring grapevine downy mildew in the field by a fluorescence-based method

Early detection of fungal pathogen presence in the field would help to better time or avoid some of the fungicide treatments used to prevent crop production losses. We recently introduced a new phytoalexin-based method for a non-invasive detection of crop diseases using their fluorescence. The causal agent of grapevine downy mildew, Plasmopara viticola, induces the synthesis of stilbenoid phytoalexins by the host, Vitis vinifera, early upon infection. These stilbenoids emit violet-blue fluorescence under UV light. A hand-held solid-state UV-LED-based field fluorimeter, named Multiplex 330, was used to measure stilbenoid phytoalexins in a vineyard. It allowed us to non-destructively detect and monitor the naturally occurring downy mildew infections on leaves in the field.

Autofluorescence: Biological functions and technical applications

Chlorophylls are the most remarkable examples of fluorophores, and their fluorescence has been intensively studied as a non-invasive tool for assessment of photosynthesis. Many other fluorophores occur in plants, such as alkaloids, phenolic compounds and porphyrins. Fluorescence could be more than just a physicochemical curiosity in the plant kingdom, as several functional roles in biocommunication occur or have been proposed. Besides, fluorescence emitted by secondary metabolites can convert damaging blue and UV into wavelengths potentially useful for photosynthesis. Detection of the fluorescence of some secondary phytochemicals may be a cue for some pollinators and/or seed dispersal organisms. Independently of their functions, plant fluorophores provide researchers with a tool that allows the visualization of some metabolites in plants and cells, complementing and overcoming some of the limitations of the use of fluorescent proteins and dyes to probe plant physiology and biochemistry. Some fluorophores are influenced by environmental interactions, allowing fluorescence to be also used as a specific stress indicator.

Proximal sensing of plant-pathogen interactions in spring barley with three fluorescence techniques

In the last years fluorescence spectroscopy has come to be viewed as an essential approach in key research fields of applied plant sciences. However, the quantity and particularly the quality of information produced by different equipment might vary considerably. In this study we investigate the potential of three optical devices for the proximal sensing of plant-pathogen interactions in four genotypes of spring barley. For this purpose, the fluorescence lifetime, the image-resolved multispectral fluorescence and selected indices of a portable multiparametric fluorescence device were recorded at 3, 6, and 9 days after inoculation (dai) from healthy leaves as well as from leaves inoculated with powdery mildew (Blumeria graminis) or leaf rust (Puccinia hordei). Genotype-specific responses to pathogen infections were revealed already at 3 dai by higher fluorescence mean lifetimes in the spectral range from 410 to 560 nm in the less susceptible varieties. Noticeable pathogen-induced modifications were also revealed by the 'Blue-to-Far-Red Fluorescence Ratio' and the 'Simple Fluorescence Ratio'. Particularly in the susceptible varieties the differences became more evident in the time-course of the experiment i.e., following the pathogen development. The relevance of the blue and green fluorescence to exploit the plant-pathogen interaction was demonstrated by the multispectral fluorescence imaging system. As shown, mildewed leaves were characterized by exceptionally high blue fluorescence, contrasting the values observed in rust inoculated leaves. Further, we confirm that the intensity of green fluorescence depends on the pathogen infection and the stage of disease development; this information might allow a differentiation of both diseases. Moreover, our results demonstrate that the detection area might influence the quality of the information, although it had a minor impact only in the current study. Finally, we highlight the relevance of different excitation-emission channels to better understand and evaluate plant-physiological alterations due to pathogen infections.

Image analysis methods for assessment of H2O2 production and Plasmopara viticola development in grapevine leaves: application to the evaluation of resistance to downy mildew

The grapevine downy mildew (Plasmopara viticola) provokes severe damages and destroys the harvest in the absence of an effective protection. Numerous fungicide treatments are thus generally necessary. To promote a sustainable production, alternative strategies of protection including new antifungal molecules, resistant genotypes or elicitor-induced resistance are under trial. To evaluate the relevance of these strategies, resistance tests are required. In this context, three image analysis methods were developed to read the results of tests performed to assess P. viticola sporulation and mycelial development, and H(2)O(2) production in leaves. They have been validated using elicitors of plant defenses. These methods are reliable, innovative, rapid, and their modular concept allows their further adaptation to other host-pathogen systems.