A Hyperspectral Library of Foliar Diseases of Wheat.

This work established a hyperspectral library of important foliar diseases of wheat induced by different fungal pathogens, representing a time series from infection to symptom appearance for the purpose of detecting spectral changes. The data were generated under controlled conditions at the leaf scale. The transition from healthy to diseased leaf tissue was assessed, and spectral shifts were identified and used in combination with histological investigations to define developmental stages in pathogenesis for each disease. The spectral signatures of each plant disease that indicate a specific developmental stage during pathogenesis, defined as turning points, were combined into a spectral library. Machine learning analysis methods were applied and compared to test the potential of this library to detect and quantify foliar diseases in hyperspectral images. All evaluated classifiers had high accuracy (≤99%) for the detection and identification of both biotrophic and necrotrophic fungi. The potential of applying spectral analysis methods in combination with a spectral library for the detection and identification of plant diseases is demonstrated. Further evaluation and development of these algorithms should contribute to a robust detection and identification system for plant diseases at different developmental stages and the promotion and development of site-specific management techniques for plant diseases under field conditions.

Assessment of Fusarium Infection and Mycotoxin Contamination of Wheat Kernels and Flour Using Hyperspectral Imaging.

Fusarium head blight (FHB) epidemics in wheat and contamination with Fusarium mycotoxins has become an increasing problem over the last decades. This prompted the need for non-invasive and non-destructive techniques to screen cereal grains for Fusarium infection, which is usually accompanied by mycotoxin contamination. This study tested the potential of hyperspectral imaging to monitor the infection of wheat kernels and flour with three Fusarium species. Kernels of two wheat varieties inoculated at anthesis with F. graminearum, F. culmorum, and F. poae were investigated. Hyperspectral images of kernels and flour were taken in the visible-near infrared (VIS-NIR) (400-1000 nm) and short-wave infrared (SWIR) (1000-2500 nm) ranges. The fungal DNA and mycotoxin contents were quantified. Spectral reflectance of Fusarium-damaged kernels (FDK) was significantly higher than non-inoculated ones. In contrast, spectral reflectance of flour from non-inoculated kernels was higher than that of FDK in the VIS and lower in the NIR and SWIR ranges. Spectral reflectance of kernels was positively correlated with fungal DNA and deoxynivalenol (DON) contents. In the case of the flour, this correlation exceeded r = -0.80 in the VIS range. Remarkable peaks of correlation appeared at 1193, 1231, 1446 to 1465, and 1742 to 2500 nm in the SWIR range.

Quantitative and qualitative phenotyping of disease resistance of crops by hyperspectral sensors: seamless interlocking of phytopathology, sensors, and machine learning is needed!

Determination and characterization of resistance reactions of crops against fungal pathogens are essential to select resistant genotypes. In plant breeding, phenotyping of genotypes is realized by time consuming and expensive visual plant ratings. During resistance reactions and during pathogenesis plants initiate different structural and biochemical defence mechanisms, which partly affect the optical properties of plant organs. Recently, intensive research has been conducted to develop innovative optical methods for an assessment of compatible and incompatible plant pathogen interaction. These approaches, combining classical phytopathology or microbiology with technology driven methods - such as sensors, robotics, machine learning, and artificial intelligence - are summarized by the term digital phenotyping. In contrast to common visual rating, detection and assessment methods, optical sensors in combination with advanced data analysis methods are able to retrieve pathogen induced changes in the physiology of susceptible or resistant plants non-invasively and objectively. Phenotyping disease resistance aims different tasks. In an early breeding step, a qualitative assessment and characterization of specific resistance action is aimed to link it, for example, to a genetic marker. Later, during greenhouse and field screening, the assessment of the level of susceptibility of different genotypes is relevant. Within this review, recent advances of digital phenotyping technologies for the detection of subtle resistance reactions and resistance breeding are highlighted and methodological requirements are critically discussed.

Comparison and Combination of Thermal, Fluorescence, and Hyperspectral Imaging for Monitoring Fusarium Head Blight of Wheat on Spikelet Scale.

Optical sensors have shown high capabilities to improve the detection and monitoring of plant disease development. This study was designed to compare the feasibility of different sensors to characterize Fusarium head blight (FHB) caused by Fusarium graminearum and Fusarium culmorum. Under controlled conditions, time-series measurements were performed with infrared thermography (IRT), chlorophyll fluorescence imaging (CFI), and hyperspectral imaging (HSI) starting 3 days after inoculation (dai). IRT allowed the visualization of temperature differences within the infected spikelets beginning 5 dai. At the same time, a disorder of the photosynthetic activity was confirmed by CFI via maximal fluorescence yields of spikelets (Fm) 5 dai. Pigment-specific simple ratio PSSRa and PSSRb derived from HSI allowed discrimination between Fusarium-infected and non-inoculated spikelets 3 dai. This effect on assimilation started earlier and was more pronounced with F. graminearum. Except the maximum temperature difference (MTD), all parameters derived from different sensors were significantly correlated with each other and with disease severity (DS). A support vector machine (SVM) classification of parameters derived from IRT, CFI, or HSI allowed the differentiation between non-inoculated and infected spikelets 3 dai with an accuracy of 78, 56 and 78%, respectively. Combining the IRT-HSI or CFI-HSI parameters improved the accuracy to 89% 30 dai.

Discovering coherency of specific gene expression and optical reflectance properties of barley genotypes differing for resistance reactions against powdery mildew.

Hyperspectral imaging has proved its potential for evaluating complex plant-pathogen interactions. However, a closer link of the spectral signatures and genotypic characteristics remains elusive. Here, we show relation between gene expression profiles and specific wavebands from reflectance during three barley-powdery mildew interactions. Significant synergistic effects between the hyperspectral signal and the corresponding gene activities has been shown using the linear discriminant analysis (LDA). Combining the data sets of hyperspectral signatures and gene expression profiles allowed a more precise differentiation of the three investigated barley-Bgh interactions independent from the time after inoculation. This shows significant synergistic effects between the hyperspectral signal and the corresponding gene activities. To analyze this coherency between spectral reflectance and seven different gene expression profiles, relevant wavelength bands and reflectance intensities for each gene were computed using the Relief algorithm. Instancing, xylanase activity was indicated by relevant wavelengths around 710 nm, which are characterized by leaf and cell structures. HvRuBisCO activity underlines relevant wavebands in the green and red range, elucidating the coherency of RuBisCO to the photosynthesis apparatus and in the NIR range due to the influence of RuBisCO on barley leaf cell development. These findings provide the first insights to links between gene expression and spectral reflectance that can be used for an efficient non-invasive phenotyping of plant resistance and enables new insights into plant-pathogen interactions.

Screening of Barley Resistance Against Powdery Mildew by Simultaneous High-Throughput Enzyme Activity Signature Profiling and Multispectral Imaging.

Molecular marker analysis allow for a rapid and advanced pre-selection and resistance screenings in plant breeding processes. During the phenotyping process, optical sensors have proved their potential to determine and assess the function of the genotype of the breeding material. Thereby, biomarkers for specific disease resistance traits provide valuable information for calibrating optical sensor approaches during early plant-pathogen interactions. In this context, the combination of physiological, metabolic phenotyping and phenomic profiles could establish efficient identification and quantification of relevant genotypes within breeding processes. Experiments were conducted with near-isogenic lines of H. vulgare (susceptible, mildew locus o (mlo) and Mildew locus a (Mla) resistant). Multispectral imaging of barley plants was daily conducted 0-8 days after inoculation (dai) in a high-throughput facility with 10 wavelength bands from 400 to 1,000 nm. In parallel, the temporal dynamics of the activities of invertase isoenzymes, as key sink specific enzymes that irreversibly cleave the transport sugar sucrose into the hexose monomers, were profiled in a semi high-throughput approach. The activities of cell wall, cytosolic and vacuole invertase revealed specific dynamics of the activity signatures for susceptible genotypes and genotypes with mlo and Mla based resistances 0-120 hours after inoculation (hai). These patterns could be used to differentiate between interaction types and revealed an early influence of Blumeria graminis f.sp. hordei (Bgh) conidia on the specific invertase activity already 0.5 hai. During this early powdery mildew pathogenesis, the reflectance intensity increased in the blue bands and at 690 nm. The Mla resistant plants showed an increased reflectance at 680 and 710 nm and a decreased reflectance in the near infrared bands from 3 dai. Applying a Support Vector Machine classification as a supervised machine learning approach, the pixelwise identification and quantification of powdery mildew diseased barley tissue and hypersensitive response spots were established. This enables an automatic identification of the barley-powdery mildew interaction. The study established a proof-of-concept for plant resistance phenotyping with multispectral imaging in high-throughput. The combination of invertase analysis and multispectral imaging showed to be a complementing validation system. This will provide a deeper understanding of optical data and its implementation into disease resistance screening.

Quantitative assessment of disease severity and rating of barley cultivars based on hyperspectral imaging in a non-invasive, automated phenotyping platform.

BACKGROUND: Phenotyping is a bottleneck for the development of new plant cultivars. This study introduces a new hyperspectral phenotyping system, which combines the high throughput of canopy scale measurements with the advantages of high spatial resolution and a controlled measurement environment. Furthermore, the measured barley canopies were grown in large containers (called Mini-Plots), which allow plants to develop field-like phenotypes in greenhouse experiments, without being hindered by pot size. RESULTS: Six barley cultivars have been investigated via hyperspectral imaging up to 30 days after inoculation with powdery mildew. With a high spatial resolution and stable measurement conditions, it was possible to automatically quantify powdery mildew symptoms through a combination of Simplex Volume Maximization and Support Vector Machines. Detection was feasible as soon as the first symptoms were visible for the human eye during manual rating. An accurate assessment of the disease severity for all cultivars at each measurement day over the course of the experiment was realized. Furthermore, powdery mildew resistance based necrosis of one cultivar was detected as well. CONCLUSION: The hyperspectral phenotyping system combines the advantages of field based canopy level measurement systems (high throughput, automatization, low manual workload) with those of laboratory based leaf level measurement systems (high spatial resolution, controlled environment, stable conditions for time series measurements). This allows an accurate and objective disease severity assessment without the need for trained experts, who perform visual rating, as well as detection of disease symptoms in early stages. Therefore, it is a promising tool for plant resistance breeding.

Specim IQ: Evaluation of a New, Miniaturized Handheld Hyperspectral Camera and Its Application for Plant Phenotyping and Disease Detection.

Hyperspectral imaging sensors are promising tools for monitoring crop plants or vegetation in different environments. Information on physiology, architecture or biochemistry of plants can be assessed non-invasively and on different scales. For instance, hyperspectral sensors are implemented for stress detection in plant phenotyping processes or in precision agriculture. Up to date, a variety of non-imaging and imaging hyperspectral sensors is available. The measuring process and the handling of most of these sensors is rather complex. Thus, during the last years the demand for sensors with easy user operability arose. The present study introduces the novel hyperspectral camera Specim IQ from Specim (Oulu, Finland). The Specim IQ is a handheld push broom system with integrated operating system and controls. Basic data handling and data analysis processes, such as pre-processing and classification routines are implemented within the camera software. This study provides an introduction into the measurement pipeline of the Specim IQ as well as a radiometric performance comparison with a well-established hyperspectral imager. Case studies for the detection of powdery mildew on barley at the canopy scale and the spectral characterization of Arabidopsis thaliana mutants grown under stressed and non-stressed conditions are presented.

A multi-resolution approach for an automated fusion of different low-cost 3D sensors.

The 3D acquisition of object structures has become a common technique in many fields of work, e.g., industrial quality management, cultural heritage or crime scene documentation. The requirements on the measuring devices are versatile, because spacious scenes have to be imaged with a high level of detail for selected objects. Thus, the used measuring systems are expensive and require an experienced operator. With the rise of low-cost 3D imaging systems, their integration into the digital documentation process is possible. However, common low-cost sensors have the limitation of a trade-off between range and accuracy, providing either a low resolution of single objects or a limited imaging field. Therefore, the use of multiple sensors is desirable. We show the combined use of two low-cost sensors, the Microsoft Kinect and the David laserscanning system, to achieve low-resolved scans of the whole scene and a high level of detail for selected objects, respectively. Afterwards, the high-resolved David objects are automatically assigned to their corresponding Kinect object by the use of surface feature histograms and SVM-classification. The corresponding objects are fitted using an ICP-implementation to produce a multi-resolution map. The applicability is shown for a fictional crime scene and the reconstruction of a ballistic trajectory.

Low-cost 3D systems: suitable tools for plant phenotyping.

Over the last few years, 3D imaging of plant geometry has become of significant importance for phenotyping and plant breeding. Several sensing techniques, like 3D reconstruction from multiple images and laser scanning, are the methods of choice in different research projects. The use of RGBcameras for 3D reconstruction requires a significant amount of post-processing, whereas in this context, laser scanning needs huge investment costs. The aim of the present study is a comparison between two current 3D imaging low-cost systems and a high precision close-up laser scanner as a reference method. As low-cost systems, the David laser scanning system and the Microsoft Kinect Device were used. The 3D measuring accuracy of both low-cost sensors was estimated based on the deviations of test specimens. Parameters extracted from the volumetric shape of sugar beet taproots, the leaves of sugar beets and the shape of wheat ears were evaluated. These parameters are compared regarding accuracy and correlation to reference measurements. The evaluation scenarios were chosen with respect to recorded plant parameters in current phenotyping projects. In the present study, low-cost 3D imaging devices have been shown to be highly reliable for the demands of plant phenotyping, with the potential to be implemented in automated application procedures, while saving acquisition costs. Our study confirms that a carefully selected low-cost sensor.

Early drought stress detection in cereals: simplex volume maximisation for hyperspectral image analysis.

Early water stress recognition is of great relevance in precision plant breeding and production. Hyperspectral imaging sensors can be a valuable tool for early stress detection with high spatio-temporal resolution. They gather large, high dimensional data cubes posing a significant challenge to data analysis. Classical supervised learning algorithms often fail in applied plant sciences due to their need of labelled datasets, which are difficult to obtain. Therefore, new approaches for unsupervised learning of relevant patterns are needed. We apply for the first time a recent matrix factorisation technique, simplex volume maximisation (SiVM), to hyperspectral data. It is an unsupervised classification approach, optimised for fast computation of massive datasets. It allows calculation of how similar each spectrum is to observed typical spectra. This provides the means to express how likely it is that one plant is suffering from stress. The method was tested for drought stress, applied to potted barley plants in a controlled rain-out shelter experiment and to agricultural corn plots subjected to a two factorial field setup altering water and nutrient availability. Both experiments were conducted on the canopy level. SiVM was significantly better than using a combination of established vegetation indices. In the corn plots, SiVM clearly separated the different treatments, even though the effects on leaf and canopy traits were subtle.