Early Detection of Plant Viral Disease Using Hyperspectral Imaging and Deep Learning

Hyperspectral imaging for quantifying Magnaporthe oryzae sporulation on rice genotypes

BACKGROUND

Precise evaluation of fungal conidia production may facilitate studies on resistance mechanisms and plant breeding for disease resistance. In this study, hyperspectral imaging (HSI) was used to quantify the sporulation of Magnaporthe oryzae on the leaves of rice cultivars grown under controlled conditions. Three rice genotypes (CO 39, Nipponbare, IR64) differing in susceptibility to blast were inoculated with M. oryzae isolates Guy 11 and Li1497. Spectral information (450-850 nm, 140 wavebands) of typical leaf blast symptoms was recorded before and after induction of sporulation of the pathogen.

RESULTS

M. oryzae produced more conidia on the highly susceptible genotype than on the moderately susceptible genotype, whereas the resistant genotype resulted in no sporulation. Changes in reflectance spectra recorded before and after induction of sporulation were significantly higher in genotype CO 39 than in Nipponbare. The spectral angle mapper algorithm for supervised classification allowed for the classification of blast symptom subareas and the quantification of lesion areas with M. oryzae sporulation. The correlation between the area under the difference spectrum (viz. spectral difference without and with sporulation) and the number of conidia per lesion and the number of conidia per lesion area was positive and count-based differences in rice - M. oryzae interaction could be reproduced in the spectral data.

CONCLUSIONS

HSI provided a precise and objective method of assessing M. oryzae conidia production on infected rice plants, revealing differences that could not be detected visually.

Machine learning in the classification of asian rust severity in soybean using hyperspectral sensor

Traditional monitoring of asian soybean rust severity is a time- and labor-intensive task, as it requires visual assessments by skilled professionals in the field. Thus, the use of remote sensing and machine learning (ML) techniques in data processing has emerged as an approach that can increase efficiency in disease monitoring, enabling faster, more accurate and time- and labor-saving evaluations. The aims of the study were: (i) to identify the spectral signature of different levels of Asian soybean rust severity; (ii) to identify the most accurate machine learning algorithm for classifying disease severity levels; (iii) which spectral input provides the highest classification accuracy for the algorithms; (iv) to determine a sample size of leaves that guarantees the best accuracy for the algorithms. A field experiment was carried out in the 2022/2023 harvest in a randomized block design with a 6x3 factorial scheme (ML algorithms x severity levels) and four replications. Disease severity levels assessed were: healthy leaves, 25 % severity, and 50 % severity. Leaf hyperspectral analysis was carried out over a wide range from 350 to 2500 nm. From this analysis, 28 spectral bands were extracted, seeking to distinguish the spectral signature for each severity level with the least input dataset. Data was subjected to machine learning analysis using Artificial Neural Network (ANN), REPTree (DT) and J48 decision trees, Random Forest (RF), and Support Vector Machine (SVM) algorithms, as well as a traditional classification method (Logistic Regression - LR). Two different input datasets were tested for each algorithm: the full spectrum (ALL) provided by the sensor and the 28 spectral bands (SB). Tests with different sample sizes were also conducted to investigate the algorithms' ability to detect severity levels with a reduced sample size. Our findings indicate differences between the spectral curves for the severity levels assessed, which makes it possible to differentiate between healthy plants with low and high severity using hyperspectral sensing. SVM was the most accurate algorithm for classifying severity levels by using all the spectral information as input. This algorithm also provided high classification accuracy when using smaller leaf samples. This study reveals that hyperspectral sensing and the use of ML algorithms provide an accurate classification of different levels of Asian rust severity, and can be powerful tools for a more efficient disease monitoring process.

High-throughput characterization and phenotyping of resistance and tolerance to virus infection in sweetpotato

Breeders have made important efforts to develop genotypes able to resist virus attacks in sweetpotato, a major crop providing food security and poverty alleviation to smallholder farmers in many regions of Sub-Saharan Africa, Asia and Latin America. However, a lack of accurate objective quantitative methods for this selection target in sweetpotato prevents a consistent and extensive assessment of large breeding populations. In this study, an approach to characterize and classify resistance in sweetpotato was established by assessing total yield loss and virus load after the infection of the three most common viruses (SPFMV, SPCSV, SPLCV). Twelve sweetpotato genotypes with contrasting reactions to virus infection were grown in the field under three different treatments: pre-infected by the three viruses, un-infected and protected from re-infection, and un-infected but exposed to natural infection. Virus loads were assessed using ELISA, (RT-)qPCR, and loop-mediated isothermal amplification (LAMP) methods, and also through multispectral reflectance and canopy temperature collected using an unmanned aerial vehicle. Total yield reduction compared to control and the arithmetic sum of (RT-)qPCR relative expression ratios were used to classify genotypes into four categories: resistant, tolerant, susceptible, and sensitives. Using 14 remote sensing predictors, machine learning algorithms were trained to classify all plots under the said categories. The study found that remotely sensed predictors were effective in discriminating the different virus response categories. The results suggest that using machine learning and remotely sensed data, further complemented by fast and sensitive LAMP assays to confirm results of predicted classifications could be used as a high throughput approach to support virus resistance phenotyping in sweetpotato breeding.

Gray mold and anthracnose disease detection on strawberry leaves using hyperspectral imaging

BACKGROUND

Gray mold and anthracnose are the main factors affecting strawberry quality and yield. Accurate and rapid early disease identification is of great significance to achieve precise targeted spraying to avoid large-scale spread of diseases and improve strawberry yield and quality. However, the characteristics between early disease infected and healthy leaves are very similar, making the early identification of strawberry gray mold and anthracnose still a challenge.

RESULTS

Based on hyperspectral imaging technology, this study explored the potential of combining spectral fingerprint features and vegetation indices (VIs) for early detection (24-h infected) of strawberry leaves diseases. The competitive adaptive reweighted sampling (CARS) algorithm and ReliefF algorithm were used for the extraction of spectral fingerprint features and VIs, respectively. Three machine learning models, Backpropagation Neural Network (BPNN), Support Vector Machine (SVM) and Random Forest (RF), were developed for the early identification of strawberry gray mold and anthracnose, using spectral fingerprint, VIs and their combined features as inputs respectively. The results showed that the combination of spectral fingerprint features and VIs had better recognition accuracy compared with individual features as inputs, and the accuracies of the three classifiers (BPNN, SVM and RF) were 97.78%, 94.44%, and 93.33%, respectively, which indicate that the fusion features approach proposed in this study can effectively improve the early detection performance of strawberry leaves diseases.

CONCLUSIONS

This study provided an accurate, rapid, and nondestructive recognition of strawberry gray mold and anthracnose disease in early stage.

Leveraging deep learning for automatic recognition of microplastics (MPs) via focal plane array (FPA) micro-FT-IR imaging

The fast and accurate identification of MPs in environmental samples is essential for the understanding of the fate and transport of MPs in ecosystems. The recognition of MPs in environmental samples by spectral classification using conventional library search routines can be challenging due to the presence of additives, surface modification, and adsorbed contaminants. Further, the thickness of MPs also impacts the shape of spectra when FTIR spectra are collected in transmission mode. To overcome these challenges, PlasticNet, a deep learning convolutional neural network architecture, was developed for enhanced MP recognition. Once trained with 8000 + spectra of virgin plastic, PlasticNet successfully classified 11 types of common plastic with accuracy higher than 95%. The errors in identification as indicated by a confusion matrix were found to be caused by edge effects, molecular similarity of plastics, and the contamination of standards. When PlasticNet was trained with spectra of virgin plastic it showed good performance (92%+) in recognizing spectra that had increased complexity due to the presence of additives and weathering. The re-training of PlasticNet with more complex spectra further enhanced the model's capability to recognize complex spectra. PlasticNet was also able to successfully identify MPs despite variations in spectra caused by variations in MP thickness. When compared with the performance of the library search in identifying MPs in the same complex dataset collected from an environmental sample, PlasticNet achieved comparable performance in identifying PP MPs, but a 17.3% improvement. PlasticNet has the potential to become a standard approach for rapid and accurate automatic recognition of MPs in environmental samples analyzed by FPA FT-IR imaging.

UAV hyperspectral remote sensor images for mango plant disease and pest identification using MD-FCM and XCS-RBFNN

To diminish disease transmission together with promoting effective management techniques, it is crucial to monitor plant health and detect pathogens earlier. The initial part in reducing losses sourced from plant diseases is to make an accurate and earlier identification. Thus, the usage of unmanned aerial vehicle (UAV) hyperspectral imaging (HSI) sensors for surveying and assessing crops, orchards, and forests has rapidly elevated over the last decade, particularly for the stress management like water, diseases, nutrition deficits, and pests. Using Minkowski Distance-based Fuzzy C Means (MD-FCM) clustering and Xavier initialization-adapted Cosine Similarity-induced Radial Bias Function Neural Network (XCS-RBFNN) techniques, a UAV HS imaging remote sensor for Spatial and Temporal Resolution (STR) of mango plant disease and pest identification is proposed in this scheme. Collecting the input UAV source (image or video) is eventuated initially along with the Region of Interest (ROI) calculated which is followed by preprocessing. Leaf segmentation is eventuated using Logistic U-net after preprocessing. Next, MD-FCM performs clustering to cluster the diseased leaves and pests individually. The disease and pest characteristics are then retrieved separately and classified further. The requisite features are then chosen from the retrieved features utilizing the Levy Flight Distribution-produced Butterfly Optimization Algorithm (LFD-BOA). Finally, the XCS-RBFNN classifier is utilized to categorize the various diseases together with pests found in the UAV input source using the chosen features. The proposed framework's experimental findings are then compared to some prevailing schemes, with the results revealing that the proposed work outperforms other benchmark techniques.

NanoViromics: long-read sequencing of dsRNA for plant virus and viroid rapid detection

There is a global need for identifying viral pathogens, as well as for providing certified clean plant materials, in order to limit the spread of viral diseases. A key component of management programs for viral-like diseases is having a diagnostic tool that is quick, reliable, inexpensive, and easy to use. We have developed and validated a dsRNA-based nanopore sequencing protocol as a reliable method for detecting viruses and viroids in grapevines. We compared our method, which we term direct-cDNA sequencing from dsRNA (dsRNAcD), to direct RNA sequencing from rRNA-depleted total RNA (rdTotalRNA), and found that it provided more viral reads from infected samples. Indeed, dsRNAcD was able to detect all of the viruses and viroids detected using Illumina MiSeq sequencing (dsRNA-MiSeq). Furthermore, dsRNAcD sequencing was also able to detect low-abundance viruses that rdTotalRNA sequencing failed to detect. Additionally, rdTotalRNA sequencing resulted in a false-positive viroid identification due to the misannotation of a host-driven read. Two taxonomic classification workflows, DIAMOND & MEGAN (DIA & MEG) and Centrifuge & Recentrifuge (Cent & Rec), were also evaluated for quick and accurate read classification. Although the results from both workflows were similar, we identified pros and cons for both workflows. Our study shows that dsRNAcD sequencing and the proposed data analysis workflows are suitable for consistent detection of viruses and viroids, particularly in grapevines where mixed viral infections are common.

Early detection of Solanum lycopersicum diseases from temporally-aggregated hyperspectral measurements using machine learning

Some plant diseases can significantly reduce harvest, but their early detection in cultivation may prevent those consequential losses. Conventional methods of diagnosing plant diseases are based on visual observation of crops, but the symptoms of various diseases may be similar. It increases the difficulty of this task even for an experienced farmer and requires detailed examination based on invasive methods conducted in laboratory settings by qualified personnel. Therefore, modern agronomy requires the development of non-destructive crop diagnosis methods to accelerate the process of detecting plant infections with various pathogens. This research pathway is followed in this paper, and an approach for classifying selected Solanum lycopersicum diseases (anthracnose, bacterial speck, early blight, late blight and septoria leaf) from hyperspectral data captured on consecutive days post inoculation (DPI) is presented. The objective of that approach was to develop a technique for detecting infection in less than seven days after inoculation. The dataset used in this study included hyperspectral measurements of plants of two cultivars of S. lycopersicum: Benito and Polfast, which were infected with five different pathogens. Hyperspectral reflectance measurements were performed using a high-spectral-resolution field spectroradiometer (350-2500 nm range) and they were acquired for 63 days after inoculation, with particular emphasis put on the first 17 day-by-day measurements. Due to a significant data imbalance and low representation of measurements on some days, the collective datasets were elaborated by combining measurements from several days. The experimental results showed that machine learning techniques can offer accurate classification, and they indicated the practical utility of our approaches.

Classification of basal stem rot using deep learning: a review of digital data collection and palm disease classification methods

Oil palm is a key agricultural resource in Malaysia. However, palm disease, most prominently basal stem rot caused at least RM 255 million of annual economic loss. Basal stem rot is caused by a fungus known as Ganoderma boninense. An infected tree shows few symptoms during early stage of infection, while potentially suffers an 80% lifetime yield loss and the tree may be dead within 2 years. Early detection of basal stem rot is crucial since disease control efforts can be done. Laboratory BSR detection methods are effective, but the methods have accuracy, biosafety, and cost concerns. This review article consists of scientific articles related to the oil palm tree disease, basal stem rot, Ganoderma Boninense, remote sensors and deep learning that are listed in the Web of Science since year 2012. About 110 scientific articles were found that is related to the index terms mentioned and 60 research articles were found to be related to the objective of this research thus included in this review article. From the review, it was found that the potential use of deep learning methods were rarely explored. Some research showed unsatisfactory results due to limitations on dataset. However, based on studies related to other plant diseases, deep learning in combination with data augmentation techniques showed great potentials, showing remarkable detection accuracy. Therefore, the feasibility of analyzing oil palm remote sensor data using deep learning models together with data augmentation techniques should be studied. On a commercial scale, deep learning used together with remote sensors and unmanned aerial vehicle technologies showed great potential in the detection of basal stem rot disease.

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

INTRODUCTION

Grapevine 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.

METHODS

Here 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.

RESULTS

When 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.

DISCUSSION

While differentiation between plants co-infected with GLRaVs and GRBV proved to be relatively challenging, both models showed promising accuracies across infection categories.

Identification and Classification of Small Sample Desert Grassland Vegetation Communities Based on Dynamic Graph Convolution and UAV Hyperspectral Imagery

Desert steppes are the last barrier to protecting the steppe ecosystem. However, existing grassland monitoring methods still mainly use traditional monitoring methods, which have certain limitations in the monitoring process. Additionally, the existing deep learning classification models of desert and grassland still use traditional convolutional neural networks for classification, which cannot adapt to the classification task of irregular ground objects, which limits the classification performance of the model. To address the above problems, this paper uses a UAV hyperspectral remote sensing platform for data acquisition and proposes a spatial neighborhood dynamic graph convolution network (SN_DGCN) for degraded grassland vegetation community classification. The results show that the proposed classification model had the highest classification accuracy compared to the seven classification models of MLP, 1DCNN, 2DCNN, 3DCNN, Resnet18, Densenet121, and SN_GCN; its OA, AA, and kappa were 97.13%, 96.50%, and 96.05% in the case of only 10 samples per class of features, respectively; The classification performance was stable under different numbers of training samples, had better generalization ability in the classification task of small samples, and was more effective for the classification task of irregular features. Meanwhile, the latest desert grassland classification models were also compared, which fully demonstrated the superior classification performance of the proposed model in this paper. The proposed model provides a new method for the classification of vegetation communities in desert grasslands, which is helpful for the management and restoration of desert steppes.

Detecting Grapevine Virus Infections in Red and White Winegrape Canopies Using Proximal Hyperspectral Sensing

Grapevine virus-associated disease such as grapevine leafroll disease (GLD) affects grapevine health worldwide. Current diagnostic methods are either highly costly (laboratory-based diagnostics) or can be unreliable (visual assessments). Hyperspectral sensing technology is capable of measuring leaf reflectance spectra that can be used for the non-destructive and rapid detection of plant diseases. The present study used proximal hyperspectral sensing to detect virus infection in Pinot Noir (red-berried winegrape cultivar) and Chardonnay (white-berried winegrape cultivar) grapevines. Spectral data were collected throughout the grape growing season at six timepoints per cultivar. Partial least squares-discriminant analysis (PLS-DA) was used to build a predictive model of the presence or absence of GLD. The temporal change of canopy spectral reflectance showed that the harvest timepoint had the best prediction result. Prediction accuracies of 96% and 76% were achieved for Pinot Noir and Chardonnay, respectively. Our results provide valuable information on the optimal time for GLD detection. This hyperspectral method can also be deployed on mobile platforms including ground-based vehicles and unmanned aerial vehicles (UAV) for large-scale disease surveillance in vineyards.

Raspberry plant stress detection using hyperspectral imaging

Monitoring plant responses to stress is an ongoing challenge for crop breeders, growers, and agronomists. The measurement of below-ground stress is particularly challenging as plants do not always show visible signs of stress in the above-ground organs, particularly at early stages. Hyperspectral imaging is a technique that could be used to overcome this challenge if associations between plant spectral data and specific stresses can be determined. In this study, three genotypes of red raspberry plants grown under controlled conditions in a glasshouse were subjected to below-ground biotic stresses (root pathogen Phytophthora rubi and root herbivore Otiorhynchus sulcatus) or abiotic stress (soil water availability) and regularly imaged using hyperspectral cameras over this period. Significant differences were observed in plant biophysical traits (canopy height and leaf dry mass) and canopy reflectance spectrum between the three genotypes and the imposed stress treatments. The ratio of reflectance at 469 and 523 nm showed a significant genotype-by-treatment interaction driven by differential genotypic responses to the P. rubi treatment. This indicates that spectral imaging can be used to identify variable plant stress responses in raspberry plants.

UAV Multisensory Data Fusion and Multi-Task Deep Learning for High-Throughput Maize Phenotyping

Recent advances in unmanned aerial vehicles (UAV), mini and mobile sensors, and GeoAI (a blend of geospatial and artificial intelligence (AI) research) are the main highlights among agricultural innovations to improve crop productivity and thus secure vulnerable food systems. This study investigated the versatility of UAV-borne multisensory data fusion within a framework of multi-task deep learning for high-throughput phenotyping in maize. UAVs equipped with a set of miniaturized sensors including hyperspectral, thermal, and LiDAR were collected in an experimental corn field in Urbana, IL, USA during the growing season. A full suite of eight phenotypes was in situ measured at the end of the season for ground truth data, specifically, dry stalk biomass, cob biomass, dry grain yield, harvest index, grain nitrogen utilization efficiency (Grain NutE), grain nitrogen content, total plant nitrogen content, and grain density. After being funneled through a series of radiometric calibrations and geo-corrections, the aerial data were analytically processed in three primary approaches. First, an extended version normalized difference spectral index (NDSI) served as a simple arithmetic combination of different data modalities to explore the correlation degree with maize phenotypes. The extended NDSI analysis revealed the NIR spectra (750-1000 nm) alone in a strong relation with all of eight maize traits. Second, a fusion of vegetation indices, structural indices, and thermal index selectively handcrafted from each data modality was fed to classical machine learning regressors, Support Vector Machine (SVM) and Random Forest (RF). The prediction performance varied from phenotype to phenotype, ranging from R² = 0.34 for grain density up to R² = 0.85 for both grain nitrogen content and total plant nitrogen content. Further, a fusion of hyperspectral and LiDAR data completely exceeded limitations of single data modality, especially addressing the vegetation saturation effect occurring in optical remote sensing. Third, a multi-task deep convolutional neural network (CNN) was customized to take a raw imagery data fusion of hyperspectral, thermal, and LiDAR for multi-predictions of maize traits at a time. The multi-task deep learning performed predictions comparably, if not better in some traits, with the mono-task deep learning and machine learning regressors. Data augmentation used for the deep learning models boosted the prediction accuracy, which helps to alleviate the intrinsic limitation of a small sample size and unbalanced sample classes in remote sensing research. Theoretical and practical implications to plant breeders and crop growers were also made explicit during discussions in the studies.

Maize disease detection based on spectral recovery from RGB images

Maize is susceptible to infect pest disease, and early disease detection is key to preventing the reduction of maize yields. The raw data used for plant disease detection are commonly RGB images and hyperspectral images (HSI). RGB images can be acquired rapidly and low-costly, but the detection accuracy is not satisfactory. On the contrary, using HSIs tends to obtain higher detection accuracy, but HSIs are difficult and high-cost to obtain in field. To overcome this contradiction, we have proposed the maize spectral recovery disease detection framework which includes two parts: the maize spectral recovery network based on the advanced hyperspectral recovery convolutional neural network (HSCNN+) and the maize disease detection network based on the convolutional neural network (CNN). Taking raw RGB data as input of the framework, the output reconstructed HSIs are used as input of disease detection network to achieve disease detection task. As a result, the detection accuracy obtained by using the low-cost raw RGB data almost as same as that obtained by using HSIs directly. The HSCNN+ is found to be fit to our spectral recovery model and the reconstruction fidelity was satisfactory. Experimental results demonstrate that the reconstructed HSIs efficiently improve detection accuracy compared with raw RGB image in tested scenarios, especially in complex environment scenario, for which the detection accuracy increases by 6.14%. The proposed framework has the advantages of fast, low cost and high detection precision. Moreover, the framework offers the possibility of real-time and precise field disease detection and can be applied in agricultural robots.

Integrated network analyses identify MYB4R1 neofunctionalization in the UV-B adaptation of Tartary buckwheat

A hallmark of adaptive evolution is innovation in gene function, which is associated with the development of distinct roles for genes during plant evolution; however, assessing functional innovation over long periods of time is not trivial. Tartary buckwheat (Fagopyrum tataricum) originated in the Himalayan region and has been exposed to intense UV-B radiation for a long time, making it an ideal species for studying novel UV-B response mechanisms in plants. Here, we developed a workflow to obtain a co-functional network of UV-B responses using data from more than 10,000 samples in more than 80 projects with multi-species and multi-omics data. Dissecting the entire network revealed that flavonoid biosynthesis was most significantly related to the UV-B response. Importantly, we found that the regulatory factor MYB4R1, which resides at the core of the network, has undergone neofunctionalization. In vitro and in vivo experiments demonstrated that MYB4R1 regulates flavonoid and anthocyanin accumulation in response to UV-B in buckwheat by binding to L-box motifs in the FtCHS, FtFLS, and FtUFGT promoters. We used deep learning to develop a visual discrimination model of buckwheat flavonoid content based on natural populations exposed to global UV-B radiation. Our study highlights the critical role of gene neofunctionalization in UV-B adaptation.

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.

Detecting Asymptomatic Infections of Rice Bacterial Leaf Blight Using Hyperspectral Imaging and 3-Dimensional Convolutional Neural Network With Spectral Dilated Convolution

Rice is one of the most important food crops for human beings. Its total production ranks third in the grain crop output. Bacterial Leaf Blight (BLB), as one of the three major diseases of rice, occurs every year, posing a huge threat to rice production and safety. There is an asymptomatic period between the infection and the onset periods, and BLB will spread rapidly and widely under suitable conditions. Therefore, accurate detection of early asymptomatic BLB is very necessary. The purpose of this study was to test the feasibility of detecting early asymptomatic infection of the rice BLB disease based on hyperspectral imaging and Spectral Dilated Convolution 3-Dimensional Convolutional Neural Network (SDC-3DCNN). First, hyperspectral images were obtained from rice leaves infected with the BLB disease at the tillering stage. The spectrum was smoothed by the Savitzky-Golay (SG) method, and the wavelength between 450 and 950 nm was intercepted for analysis. Then Principal Component Analysis (PCA) and Random Forest (RF) were used to extract the feature information from the original spectra as inputs. The overall performance of the SDC-3DCNN model with different numbers of input features and different spectral dilated ratios was evaluated. Lastly, the saliency map visualization was used to explain the sensitivity of individual wavelengths. The results showed that the performance of the SDC-3DCNN model reached an accuracy of 95.4427% when the number of inputs is 50 characteristic wavelengths (extracted by RF) and the dilated ratio is set at 5. The saliency-sensitive wavelengths were identified in the range from 530 to 570 nm, which overlaps with the important wavelengths extracted by RF. According to our findings, combining hyperspectral imaging and deep learning can be a reliable approach for identifying early asymptomatic infection of the rice BLB disease, providing sufficient support for early warning and rice disease prevention.

Novel Vegetation Indices to Identify Broccoli Plants Infected With Xanthomonas campestris pv. campestris

A rapid diagnosis of black rot in brassicas, a devastating disease caused by Xanthomonas campestris pv. campestris (Xcc), would be desirable to avoid significant crop yield losses. The main aim of this work was to develop a method of detection of Xcc infection on broccoli leaves. Such method is based on the use of imaging sensors that capture information about the optical properties of leaves and provide data that can be implemented on machine learning algorithms capable of learning patterns. Based on this knowledge, the algorithms are able to classify plants into categories (healthy and infected). To ensure the robustness of the detection method upon future alterations in climate conditions, the response of broccoli plants to Xcc infection was analyzed under a range of growing environments, taking current climate conditions as reference. Two projections for years 2081-2100 were selected, according to the Assessment Report of Intergovernmental Panel on Climate Change. Thus, the response of broccoli plants to Xcc infection and climate conditions has been monitored using leaf temperature and five conventional vegetation indices (VIs) derived from hyperspectral reflectance. In addition, three novel VIs, named diseased broccoli indices (DBI₁-DBI₃), were defined based on the spectral reflectance signature of broccoli leaves upon Xcc infection. Finally, the nine parameters were implemented on several classifying algorithms. The detection method offering the best performance of classification was a multilayer perceptron-based artificial neural network. This model identified infected plants with accuracies of 88.1, 76.9, and 83.3%, depending on the growing conditions. In this model, the three Vis described in this work proved to be very informative parameters for the disease detection. To our best knowledge, this is the first time that future climate conditions have been taken into account to develop a robust detection model using classifying algorithms.

Hyperspectral imaging and machine learning in food microbiology: Developments and challenges in detection of bacterial, fungal, and viral contaminants

Hyperspectral imaging (HSI) is a robust and nondestructive method that can detect foreign particles such as microbial, chemical, and physical contamination in food. This review summarizes the work done in the last two decades in this field with a highlight on challenges, risks, and research gaps. Considering the challenges of using HSI on complex matrices like food (e.g., the confounding and masking effects of background signals), application of machine learning and modeling approaches that have been successful in achieving better accuracy as well as increasing the detection limit have also been discussed here. Foodborne microbial contaminants such as bacteria, fungi, viruses, yeast, and protozoa are of interest and concern to food manufacturers due to the potential risk of either food poisoning or food spoilage. Detection of these contaminants using fast and efficient methods would not only prevent outbreaks and recalls but will also increase consumer acceptance and demand for shelf-stable food products. The conventional culture-based methods for microbial detection are time and labor-intensive, whereas hyperspectral imaging (HSI) is robust, nondestructive with minimum sample preparation, and has gained significant attention due to its rapid approach to detection of microbial contaminants. This review is a comprehensive summary of the detection of bacterial, viral, and fungal contaminants in food with detailed emphasis on the specific modeling and datamining approaches used to overcome the specific challenges associated with background and data complexity.

Rice bacterial blight resistant cultivar selection based on visible/near-infrared spectrum and deep learning

BACKGROUND

Rice bacterial blight (BB) has caused serious damage in rice yield and quality leading to huge economic loss and food safety problems. Breeding disease resistant cultivar becomes the eco-friendliest and most effective alternative to regulate its outburst, since the propagation of pathogenic bacteria is restrained. However, the BB resistance cultivar selection suffers tremendous labor cost, low efficiency, and subjective human error. And dynamic rice BB phenotyping study is absent from exploring the pattern of BB growth with different genotypes.

RESULTS

In this paper, with the aim of alleviating the labor burden of plant breeding experts in the resistant cultivar screening processing and exploring the disease resistance phenotyping variation pattern, visible/near-infrared (VIS-NIR) hyperspectral images of rice leaves from three varieties after inoculation were collected and sent into a self-built deep learning model LPnet for disease severity assessment. The growth status of BB lesion at the time scale was fully revealed. On the strength of the attention mechanism inside LPnet, the most informative spectral features related to lesion proportion were further extracted and combined into a novel and refined leaf spectral index. The effectiveness and feasibility of the proposed wavelength combination were verified by identifying the resistant cultivar, assessing the resistant ability, and spectral image visualization.

CONCLUSIONS

This study illustrated that informative VIS-NIR spectrums coupled with attention deep learning had great potential to not only directly assess disease severity but also excavate spectral characteristics for rapid screening disease resistant cultivars in high-throughput phenotyping.

Plant Viral Disease Detection: From Molecular Diagnosis to Optical Sensing Technology—A Multidisciplinary Review

Plant viral diseases result in productivity and economic losses to agriculture, necessitating accurate detection for effective control. Lab-based molecular testing is the gold standard for providing reliable and accurate diagnostics; however, these tests are expensive, time-consuming, and labour-intensive, especially at the field-scale with a large number of samples. Recent advances in optical remote sensing offer tremendous potential for non-destructive diagnostics of plant viral diseases at large spatial scales. This review provides an overview of traditional diagnostic methods followed by a comprehensive description of optical sensing technology, including camera systems, platforms, and spectral data analysis to detect plant viral diseases. The paper is organized along six multidisciplinary sections: (1) Impact of plant viral disease on plant physiology and consequent phenotypic changes, (2) direct diagnostic methods, (3) traditional indirect detection methods, (4) optical sensing technologies, (5) data processing techniques and modelling for disease detection, and (6) comparison of the costs. Finally, the current challenges and novel ideas of optical sensing for detecting plant viruses are discussed.

Optical imaging spectroscopy for rapid, primary screening of SARS-CoV-2: a proof of concept

Effective testing is essential to control the coronavirus disease 2019 (COVID-19) transmission. Here we report a-proof-of-concept study on hyperspectral image analysis in the visible and near-infrared range for primary screening at the point-of-care of SARS-CoV-2. We apply spectral feature descriptors, partial least square-discriminant analysis, and artificial intelligence to extract information from optical diffuse reflectance measurements from 5 µL fluid samples at pixel, droplet, and patient levels. We discern preparations of engineered lentiviral particles pseudotyped with the spike protein of the SARS-CoV-2 from those with the G protein of the vesicular stomatitis virus in saline solution and artificial saliva. We report a quantitative analysis of 72 samples of nasopharyngeal exudate in a range of SARS-CoV-2 viral loads, and a descriptive study of another 32 fresh human saliva samples. Sensitivity for classification of exudates was 100% with peak specificity of 87.5% for discernment from PCR-negative but symptomatic cases. Proposed technology is reagent-free, fast, and scalable, and could substantially reduce the number of molecular tests currently required for COVID-19 mass screening strategies even in resource-limited settings.

Making Sense of Light: The Use of Optical Spectroscopy Techniques in Plant Sciences and Agriculture

As a result of the development of non-invasive optical spectroscopy, the number of prospective technologies of plant monitoring is growing. Being implemented in devices with different functions and hardware, these technologies are increasingly using the most advanced data processing algorithms, including machine learning and more available computing power each time. Optical spectroscopy is widely used to evaluate plant tissues, diagnose crops, and study the response of plants to biotic and abiotic stress. Spectral methods can also assist in remote and non-invasive assessment of the physiology of photosynthetic biofilms and the impact of plant species on biodiversity and ecosystem stability. The emergence of high-throughput technologies for plant phenotyping and the accompanying need for methods for rapid and non-contact assessment of plant productivity has generated renewed interest in the application of optical spectroscopy in fundamental plant sciences and agriculture. In this perspective paper, starting with a brief overview of the scientific and technological backgrounds of optical spectroscopy and current mainstream techniques and applications, we foresee the future development of this family of optical spectroscopic methodologies.

Current State of Hyperspectral Remote Sensing for Early Plant Disease Detection: A Review

The development of hyperspectral remote sensing equipment, in recent years, has provided plant protection professionals with a new mechanism for assessing the phytosanitary state of crops. Semantically rich data coming from hyperspectral sensors are a prerequisite for the timely and rational implementation of plant protection measures. This review presents modern advances in early plant disease detection based on hyperspectral remote sensing. The review identifies current gaps in the methodologies of experiments. A further direction for experimental methodological development is indicated. A comparative study of the existing results is performed and a systematic table of different plants' disease detection by hyperspectral remote sensing is presented, including important wave bands and sensor model information.

Novel CropdocNet Model for Automated Potato Late Blight Disease Detection from Unmanned Aerial Vehicle-Based Hyperspectral Imagery

The accurate and automated diagnosis of potato late blight disease, one of the most destructive potato diseases, is critical for precision agricultural control and management. Recent advances in remote sensing and deep learning offer the opportunity to address this challenge. This study proposes a novel end-to-end deep learning model (CropdocNet) for accurate and automated late blight disease diagnosis from UAV-based hyperspectral imagery. The proposed method considers the potential disease-specific reflectance radiation variance caused by the canopy’s structural diversity and introduces multiple capsule layers to model the part-to-whole relationship between spectral–spatial features and the target classes to represent the rotation invariance of the target classes in the feature space. We evaluate the proposed method with real UAV-based HSI data under controlled and natural field conditions. The effectiveness of the hierarchical features is quantitatively assessed and compared with the existing representative machine learning/deep learning methods on both testing and independent datasets. The experimental results show that the proposed model significantly improves accuracy when considering the hierarchical structure of spectral–spatial features, with average accuracies of 98.09% for the testing dataset and 95.75% for the independent dataset, respectively.

Unmanned Aerial Vehicles (UAV) in Precision Agriculture: Applications and Challenges

Agriculture is the primary source of income in developing countries like India. Agriculture accounts for 17 percent of India’s total GDP, with almost 60 percent of the people directly or indirectly employed. While researchers and planters focus on a variety of elements to boost productivity, crop loss due to disease is one of the most serious issues they confront. Crop growth monitoring and early detection of pest infestations are still a problem. With the expansion of cultivation to wider fields, manual intervention to monitor and diagnose insect and pest infestations is becoming increasingly difficult. Failure to apply on time fertilizers and pesticides results in more crop loss and so lower output. Farmers are putting in greater effort to conserve crops, but they are failing most of the time because they are unable to adequately monitor the crops when they are infected by pests and insects. Pest infestation is also difficult to predict because it is not evenly distributed. In the recent past, modern equipment, tools, and approaches have been used to replace manual involvement. Unmanned aerial vehicles serve a critical role in crop disease surveillance and early detection in this setting. This research attempts to give a review of the most successful techniques to have precision-based crop monitoring and pest management in agriculture fields utilizing unmanned aerial vehicles (UAVs) or unmanned aircraft. The researchers’ reports on the various types of UAVs and their applications to early detection of agricultural diseases are rigorously assessed and compared. This paper also discusses the deployment of aerial, satellite, and other remote sensing technologies for disease detection, as well as their Quality of Service (QoS).

The Promise of Hyperspectral Imaging for the Early Detection of Crown Rot in Wheat

Crown rot disease is caused by Fusarium pseudograminearum and is one of the major stubble-soil fungal diseases threatening the cereal industry globally. It causes failure of grain establishment, which brings significant yield loss. Screening crops affected by crown rot is one of the key tools to manage crown rot, because it is necessary to understand disease infection conditions, identify the severity of infection, and discover potential resistant varieties. However, screening crown rot is challenging as there are no clear visible symptoms on leaves at early growth stages. Hyperspectral imaging (HSI) technologies have been successfully used to better understand plant health and disease incidence, including light absorption rate, water and nutrient distribution, and disease classification. This suggests HSI imaging technologies may be used to detect crown rot at early growing stages, however, related studies are limited. This paper briefly describes the symptoms of crown rot disease and traditional screening methods with their limitations. It, then, reviews state-of-art imaging technologies for disease detection, from color imaging to hyperspectral imaging. In particular, this paper highlights the suitability of hyperspectral-based screening methods for crown rot disease. A hypothesis is presented that HSI can detect crown-rot-infected plants before clearly visible symptoms on leaves by sensing the changes of photosynthesis, water, and nutrients contents of plants. In addition, it describes our initial experiment to support the hypothesis and further research directions are described.

Grapevine Virology in the Third-Generation Sequencing Era: From Virus Detection to Viral Epitranscriptomics

Among all economically important plant species in the world, grapevine (Vitis vinifera L.) is the most cultivated fruit plant. It has a significant impact on the economies of many countries through wine and fresh and dried fruit production. In recent years, the grape and wine industry has been facing outbreaks of known and emerging viral diseases across the world. Although high-throughput sequencing (HTS) has been used extensively in grapevine virology, the application and potential of third-generation sequencing have not been explored in understanding grapevine viruses and their impact on the grapevine. Nanopore sequencing, a third-generation technology, can be used for the direct sequencing of both RNA and DNA with minimal infrastructure. Compared to other HTS methods, the MinION nanopore platform is faster and more cost-effective and allows for long-read sequencing. Due to the size of the MinION device, it can be easily carried for field viral disease surveillance. This review article discusses grapevine viruses, the principle of third-generation sequencing platforms, and the application of nanopore sequencing technology in grapevine virus detection, virus-plant interactions, as well as the characterization of viral RNA modifications.

Hyperspectral image processing for the identification and quantification of lentiviral particles in fluid samples

Optical spectroscopic techniques have been commonly used to detect the presence of biofilm-forming pathogens (bacteria and fungi) in the agro-food industry. Recently, near-infrared (NIR) spectroscopy revealed that it is also possible to detect the presence of viruses in animal and vegetal tissues. Here we report a platform based on visible and NIR (VNIR) hyperspectral imaging for non-contact, reagent free detection and quantification of laboratory-engineered viral particles in fluid samples (liquid droplets and dry residue) using both partial least square-discriminant analysis and artificial feed-forward neural networks. The detection was successfully achieved in preparations of phosphate buffered solution and artificial saliva, with an equivalent pixel volume of 4 nL and lowest concentration of 800 TU·\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\upmu$$\end{document}μL⁻¹. This method constitutes an innovative approach that could be potentially used at point of care for rapid mass screening of viral infectious diseases and monitoring of the SARS-CoV-2 pandemic.

4D surface shape measurement system with high spectral resolution and great depth accuracy

A 4D surface shape measurement system that combines spectral detection and 3D surface morphology measurements is proposed, which can realize high spectral resolution and great depth accuracy (HSDA system). A starring hyperspectral imager system based on a grating generates precise spectral data, while a structured light stereovision system reconstructs target morphology as a 3D point cloud. The systems are coupled using a double light path module, which realize point-to-point correspondence of the systems' image planes. The spectral and 3D coordinate data are fused and transformed into a 4D data set. The HSDA system has excellent performance with a spectral resolution of 3 nm and depth accuracy of 27.5 μm. A range of 4D imaging experiments are presented to demonstrate the capabilities and versatility of the HSDA system, which show that it can be used in broad range of application areas, such as fluorescence detection, face anti-spoofing, physical health state assessment and green plant growth condition monitoring.