Model Agnostic Meta-Learning(MAML)-Based Ensemble Model for Accurate Detection of Wheat Diseases Using Vision Transformer and Graph Neural Networks

Wheat is a critical crop,extensively consumed worldwide,and its production enhancement is essential to meet escalating demand.The presence of diseases like stem rust,leaf rust,yellow rust,and tan spot significantly diminishes wheat yield,making the early and precise identification of these diseases vital for effective disease management.With advancements in deep learning algorithms,researchers have proposed many methods for the automated detection of disease pathogens;however,accurately detectingmultiple disease pathogens simultaneously remains a challenge.This challenge arises due to the scarcity of RGB images for multiple diseases,class imbalance in existing public datasets,and the difficulty in extracting features that discriminate between multiple classes of disease pathogens.In this research,a novel method is proposed based on Transfer Generative Adversarial Networks for augmenting existing data,thereby overcoming the problems of class imbalance and data scarcity.This study proposes a customized architecture of Vision Transformers(ViT),where the feature vector is obtained by concatenating features extracted from the custom ViT and Graph Neural Networks.This paper also proposes a Model AgnosticMeta Learning(MAML)based ensemble classifier for accurate classification.The proposedmodel,validated on public datasets for wheat disease pathogen classification,achieved a test accuracy of 99.20%and an F1-score of 97.95%.Compared with existing state-of-the-art methods,this proposed model outperforms in terms of accuracy,F1-score,and the number of disease pathogens detection.In future,more diseases can be included for detection along with some other modalities like pests and weed.

Fusion of Region Extraction and Cross-Entropy SVM Models for Wheat Rust Diseases Classification

Wheat rust diseases are one of the major types of fungal diseases that cause substantial yield quality losses of 15%–20%every year.The wheat rust diseases are identified either through experienced evaluators or computerassisted techniques.The experienced evaluators take time to identify the disease which is highly laborious and too costly.If wheat rust diseases are predicted at the development stages,then fungicides are sprayed earlier which helps to increase wheat yield quality.To solve the experienced evaluator issues,a combined region extraction and cross-entropy support vector machine(CE-SVM)model is proposed for wheat rust disease identification.In the proposed system,a total of 2300 secondary source images were augmented through flipping,cropping,and rotation techniques.The augmented images are preprocessed by histogram equalization.As a result,preprocessed images have been applied to region extraction convolutional neural networks(RCNN);Fast-RCNN,Faster-RCNN,and Mask-RCNN models for wheat plant patch extraction.Different layers of region extraction models construct a feature vector that is later passed to the CE-SVM model.As a result,the Gaussian kernel function in CE-SVM achieves high F1-score(88.43%)and accuracy(93.60%)for wheat stripe rust disease classification.

Wheat Genetic Transformation as Efficient Tools to Fight against Fungal Diseases

Wheat ranks first among cereal crops cultivated in the world. In its production, diseases like powdery mildew, fusarium head blight and rusts caused by fungal pathogens represent a major problem. They produce different symptoms that cause severe crop damage by infecting the spikes, leaves, roots, stems and grains. They are causing losses both by reducing the quantity of the harvested crop and the quality of the product. Quality problems of the harvested product can be due to shrivelled seed, which are frequently found as a consequence of the infection by leaf pathogens, such as mildews, rusts and Septoria. Fusarium head blight is the major culprit for mycotoxin contamination from the harvested grain, causing economic losses and in the worst casing human and animal health problems. In severe epidemics, all these fungal diseases can significantly reduce yield. Resistance to fungi is beneficial not only from a commercial point of view （yield）, but also because of the reduced levels of mycotoxins. The integration of transgenic approaches offers a potential chemical-free and environment-friendly solution for controlling fungal pathogens. This is an essential asset for wheat world food security.

Control Efficacy and Antifungal Mechanism of Bacillus Cereus Strain JK14 against Wheat Take-all Disease

[Objective] Study on control efficacy and inhibitory effect of Bacillus cereus strain JK14^·against wheat take-all disease, investigating its antifungal mechanism. [Method] B. cereus JK14^· was isolated from soil in the rhizosphere of wheat, inhibitory effects of whose nutrient solution form against Gaeumannomyces graminis var tritici strains 9862 and 9812 were measured in laboratory and then for its antifungal mechanism. The strain JK14^· with rifampicin and wheat take-all disease resistance was screened by increasing concentration of the two substrates, and colonization of JK14^·was studied. [Result] In pot experiment, the control effects of JK14^·, against 9862 and 9812 are 63% and 59%, respectively, which are higher than that of chemical fungicides, with 55% and 51% , respectively. JK14^· could deform mycelium and causes degradation of cell wall. And there are also dynamic change of JK14^· in root system. JK14^· on seed could extend to root along with seed germination and rooting, but per unit tissue mycelium number decreased gradually. [Conclusion] The results indicate some control efficacy of B. cereus strain JK14^· against wheat take-all disease.

A Convolutional Neural Network Model for Wheat Crop Disease Prediction

Wheat is the most important cereal crop,and its low production incurs import pressure on the economy.It fulfills a significant portion of the daily energy requirements of the human body.The wheat disease is one of the major factors that result in low production and negatively affects the national economy.Thus,timely detection of wheat diseases is necessary for improving production.The CNN-based architectures showed tremendous achievement in the image-based classification and prediction of crop diseases.However,these models are computationally expensive and need a large amount of training data.In this research,a light weighted modified CNN architecture is proposed that uses eight layers particularly,three convolutional layers,three SoftMax layers,and two flattened layers,to detect wheat diseases effectively.The high-resolution images were collected from the fields in Azad Kashmir(Pakistan)and manually annotated by three human experts.The convolutional layers use 16,32,and 64 filters.Every filter uses a 3×3 kernel size.The strides for all convolutional layers are set to 1.In this research,three different variants of datasets are used.These variants S1-70%:15%:15%,S2-75%:15%:10%,and S3-80%:10%:10%(train:validation:test)are used to evaluate the performance of the proposed model.The extensive experiments revealed that the S3 performed better than S1 and S2 datasets with 93%accuracy.The experiment also concludes that a more extensive training set with high-resolution images can detect wheat diseases more accurately.

Screening and Identification of Biocontrol Strains against Bipolaris sorokiniana

Bipolaris sorokiniana is an important disease causing wheat root rot. Different biocontrol strains were screened with the pathogen as the target. A total of 210 strains of bacteria and fungi preserved in the laboratory were preliminarily and secondarily screened by plate confrontation culture. The 17 strains of bacteria and 36 strains of fungi with good bicontrol effect were screened. Eventually, the best fungal strain and the best bacterial strain were obtained. The ITS fragments of fungi were amplified by PCR, and the target band of 571 bp was obtained. The 16 S gene frag-ments of bacteria were amplified by PCR, and the target band of 1 455 bp was obtained. Through morphological observation, the screened strains were identified. Finally, the bicontrol fungus was confirmed as Trichoderma asperellum and the bacterium was Bacillus amylofaciens.

Genetic Analysis of Stripe Rust Resistance of Xikemai 6 at Adult Plant Stage

To confirm resistance and genetic rules of Xikemai 6 against physiological races of wheat stripe rust,physiological races CYR31,CYR32 and CYR33,Su11-4 and V26 were inoculated in Xikemai 6 and Mingxian 169 and their hybrid progenies F_1,F_2 and F_3 at adult plant stage on March 2015. The results showed that the resistance of Xikemai 6 against CYR31 was controlled by 2 pairs of dominant genes and a pair of recessive genes; the resistance against CYR32 was controlled by three pairs of dominant resistant genes（ two pairs of genes performed cumulative effect）; the resistance against CYR33 was controlled by a pair of dominant genes and a pair of recessive genes; the resistance against Su11-4 was controlled by a pair of dominant genes and a pair of recessive genes independently or collaboratively; the resistance against V26 was controlled by a pair of dominant genes independently. Due to good performance of Xikemai 6 in test and production,as well as years of resistance identification and genetic analysis,Xikemai 6 was proved to be an excellent cultivar with good resistance against stripe rust,and the inheritance of its resistance was stable,so Xikemai 6 could be used as a germplasm resource and resistance material with excellent comprehensive character. Molecular marker and localization could be further studied,to provide new resistance parents for disease-resistant breeding of wheat.

Novel method for identifying wheat leaf disease images based on differential amplification convolutional neural network

In this study,a differential amplification convolutional neural network(DACNN)was proposed and used in the identification of wheat leaf disease images with ideal accuracy.The branches added between the deep convolutional layers can amplify small differences between the real output and the expected output,which made the weight updating more sensitive to the light errors return in the backpropagation pass and significantly improved the fitting capability.Firstly,since there is no large-scale wheat leaf disease images dataset at present,the wheat leaf disease dataset was constructed which included eight kinds of wheat leaf images,and five kinds of data augmentation methods were used to expand the dataset.Secondly,DACNN combined four classifiers:Softmax,support vector machine(SVM),K-nearest neighbor(KNN)and Random Forest to evaluate the wheat leaf disease dataset.Finally,the DACNN was compared with the models:LeNet-5,AlexNet,ZFNet and Inception V3.The extensive results demonstrate that DACNN is better than other models.The average recognition accuracy obtained on the wheat leaf disease dataset is 95.18%.

Papiliotrema flavescens colonized in biochars inhibits wheat crown rot and Fusarium head blight

Biochar,a known soil amendment,has been found to alleviate plant or soil-borne diseases.However,the related mechanisms are poorly understood,especially from the perspective of microbes colonizing in raw biochar.In this study,laboratory studies,including isolation,adsorption,antifungal test,were employed to investigate biological characteristic of a fungus isolated from aging biochars(peanut shell biochar,rice husk biochar and bamboo biochar),as well as antimicrobial mechanisms on Fusarium species which cause wheat crown rot and Fusarium head blight(FHB).Furthermore,the field trial was conducted to investigate the effect of this fungus on spikelet disease rate and crop yield.The results were as follows:the isolated fungus was identified as Papiliotrema flavescens(P.flavescens),which was confirmed from ambient air,and its properties were characterized,such as the optimal growth pH and the growth curve.The mixed action of 1×10^(6)cells/mL P.flavescens and 1×10^(6)cells/mL Bacillus subtilis(B.subtilis)had the best antifungal effect,reaching an antifungal rate of 86.5%.The P.fla-vescens exerted antifungal effects through potential competition among nutrition,space,and parasitism,not from producing antifungal substances.Results from the field trial showed that the presence of P.flavescens could reduce the spike disease rate by 43.2%and increase the yield by 34.5%.In summary,the present study provides novel evidence about microbes from aging biochars that can prevent wheat crown rot and FHB.

Inhibition of mycotoxin deoxynivalenol generation by using selenized glucose

Selenized glucose can be easily prepared via the selenization reaction of glucose using in situ generated NaHSe as the selenization reagent.The technique has been industrialized to produce the chemical in kilogram scale,making it an easily available mate rial in laborato ry presently.The selenized glucose may be widely used as the starting material for the preparation of selenium-containing catalysts,as the organoselenium additive for feeds,and as the efficient selenium-enriched foliar fertilizers.In this work,we found that treating Fusarium graminearum,a fungal pathogen inciting wheat scab disease,with selenium glucose could significantly inhibit the generation of the deoxynivalenol(DON)toxin,which might be a breakthrough for reducing the detriment of the wheat scab disease.