Combining Random Forest and XGBoost Methods in Detecting Early and Mid-Term Winter Wheat Stripe Rust Using Canopy Level Hyperspectral Measurements

Appropriate modeling methods and feature selection algorithms must be selected to improve the accuracy of early and mid-term remote sensing detection of wheat stripe rust. In the current study, we explored the effectiveness of the random forest (RF) algorithm combined with the extreme gradient boosting (XGboost) method for early and mid-term wheat stripe rust detection based on the vegetation indices extracted from canopy level hyperspectral measurements. Initially, 21 vegetation indices that were related to the early and mid-term winter wheat stripe rust were calculated on the basis of canopy level hyperspectral reflectance. Subsequently, the optimal vegetation index combination for disease detection was determined using correlation analysis (CA) combined with RF algorithms. Then, the disease severity detection model of early and mid-term winter wheat stripe rust was constructed using XGBoost method based on the optimal vegetation index combination. For the evaluation and comparison of the initial results, three commonly used classification methods, namely, RF, backpropagation neural network (BPNN), and support vector machine (SVM), were utilized. The vegetation index combinations determined by the single CA algorithm were also used to construct detection models. Compared with the detection models based on the vegetation index combination obtained using the single CA algorithm, the overall accuracy of the four detection models based on the optimal vegetation index combination based on CA combined with RF algorithms increased by 16.1% (XGBoost), 9.7% (RF), 8.1% (SVM), and 8.1% (BPNN). Among the eight models, the XGBoost detection model based on the optimal vegetation index combination using CA combined with RF algorithms, CA-RF-XGBoost, achieved the highest overall accuracy of 87.1% and the highest kappa coefficient of 0.798. Our results indicate that the RF combined with XGBoost can improve the detection accuracy of early and mid-term winter wheat stripe rust effectively at canopy scale.

Protective role of foliar application of green-synthesized silver nanoparticles against wheat stripe rust disease caused by Puccinia striiformis

Green-synthesized nanoparticles have a tremendous antimicrobial potential to be used as an alternative to hazardous fungicides. In this study, the green synthesis of silver nanoparticles (AgNPs) was performed by using Moringa oleifera leaf extract as a reducing and stabilizing agent. The synthesized AgNPs were subjected to different characterization techniques. UV-visible spectroscopy confirmed the surface plasmon resonance band in the range of 400–450 nm, and zeta analysis revealed that the synthesized AgNPs ranged 4–30 nm in size. Scanning electron microscopy depicted tiny fused rectangular segments and the crystalline nature of the synthesized AgNPs was confirmed using X-ray diffraction. Energy dispersive X-ray (EDX) detector confirmed the presence of metallic silver ions. Fourier-transform infrared analysis revealed the presence of phenols as main reducing agents in the plant extract. Foliar application of different concentrations (25, 50, 75, and 100 ppm) of AgNPs was applied on wheat plants inoculated with Puccinia striiformis to assess the disease incidence against stripe rust disease. AgNPs at a conc. of 75 ppm were found to be more effective against wheat stripe rust disease. Furthermore, the application of AgNPs enhanced morpho-physiological attributes and reduced nonenzymatic compounds and antioxidant enzymes in wheat. The present study highlights the potential role of the green-synthesized AgNPs as a biological control of yellow rust disease.

Bacterial Coated Fertilizer Induced Resistance Against Wheat Stripe Rust

Wheat is the second largest consumed cereal by humans after Rice and its high yield and production is very critical for ever increasing global population. The wheat crop is grown all over Pakistan and threatened by several limiting factors. Stripe rust, caused by Puccinia striiformis, is the most destructive wheat pathogen and can reduce yield up to 70% in Pakistan. The present study aimed at exploring the role of Zabardast urea, a bacterial coated urea with zinc, in inducing resistance against wheat stripe rust. The study involved the collection and maintenance of stripe rust inoculum on Morroco cultivar which later used to inoculate seedlings of Akbar-2019 and Galaxy-2019 resistant and susceptible varieties with three different fertilizer levels viz. specialty fertilizer zabardast urea, plain urea with zinc and plain urea. The results demonstrated the positive role of bacterial coated urea with zinc and reduced the disease severity by 10% and 5% in susceptible and resistant cultivars, respectively, leaving resistant variety asymptomatic. The plain urea with zinc also decreased disease severity in susceptible variety Galaxy-2013 by 6% in comparison with plain urea treatment underlying the role of zinc in combating stripe rust. The study underlines the importance of specialty fertilizers in inducing resistance against stripe rust in wheat and needs further experimentation exploring the mechanisms involved in disease resistance under field conditions.

Yield losses associated with different levels of stripe rust resistance of commercial wheat cultivars in China

Wheat stripe rust is one of the most destructive diseases to affect wheat. Although the major resistant wheat varieties have made a great contribution to the global food security, yield losses due to the stripe rust still occurs in the large wheat growing areas when climatic conditions are unstable. Despite this threat, resistance levels and yield losses of these elite wheat cultivars under wheat stripe rust infection have not been well studied. Based on the present investigation of natural infection conditions over two years, analysis of the area under the disease progress curves (AUDPC) differentiated susceptible cultivars Mianmai 367 (MM367) (788.59), Jinmai 47 (JM47) (1087.71), and Avocet Susceptible (AvS) (1314.59) from resistant cultivars Xikemai 18 (XKM18) (177.50) and Xiaoyan 6 (XY6) (545.67). Stripe rust resulted in a two-year mean yield loss of 32% for all tested varieties. The susceptible varieties JM47, AvS, and MM367 lost 64%, 55%, and 21% of grain yield, respectively. On the contrary, rust-resistant cultivars XKM18 and XY6 lost only 11% and 28%, respectively. In addition, stripe rust resulted in reduced kernel hardness (KH), flour yield (FY), and flour whiteness (FW). Dough and gluten properties were also affected. Overall, results revealed that the grain yield and quality loss of the resistant wheat cultivars were less than in the susceptible cultivars. Disease-resistant cultivars such as XKM18 should be promoted and recommended for application. It may also be suggested that growing a susceptible variety such as MM367 could be feasible in combination with fungicide application under high disease pressure.

The barley immune receptor Mla recognizes multiple pathogens and contributes to host range dynamics

Crop losses caused by plant pathogens are a primary threat to stable food production. Stripe rust (Puccinia striiformis) is a fungal pathogen of cereal crops that causes significant, persistent yield loss. Stripe rust exhibits host species specificity, with lineages that have adapted to infect wheat and barley. While wheat stripe rust and barley stripe rust are commonly restricted to their corresponding hosts, the genes underlying this host specificity remain unknown. Here, we show that three resistance genes, Rps6, Rps7, and Rps8, contribute to immunity in barley to wheat stripe rust. Rps7 cosegregates with barley powdery mildew resistance at the Mla locus. Using transgenic complementation of different Mla alleles, we confirm allele-specific recognition of wheat stripe rust by Mla. Our results show that major resistance genes contribute to the host species specificity of wheat stripe rust on barley and that a shared genetic architecture underlies resistance to the adapted pathogen barley powdery mildew and non-adapted pathogen wheat stripe rust.

Prediction of Wheat Stripe Rust Occurrence with Time Series Sentinel-2 Images

Wheat stripe rust has a severe impact on wheat yield and quality. An effective prediction method is necessary for food security. In this study, we extract the optimal vegetation indices (VIs) sensitive to stripe rust at different time-periods, and develop a wheat stripe rust prediction model with satellite images to realize the multi-temporal prediction. First, VIs related to stripe rust stress are extracted as candidate features for disease prediction from time series Sentinel-2 images. Then, the optimal VI combinations are selected using sequential forward selection (SFS). Finally, the occurrence of wheat stripe rust in different time-periods is predicted using the support vector machine (SVM) method. The results of the features selected demonstrate that, before the jointing period, the optimal VIs are related to the biomass, pigment, and moisture of wheat. After the jointing period, the red-edge VIs related to the crop health status play important roles. The overall accuracy and Kappa coefficient of the prediction model, which is based on SVM, is generally higher than those of the k-nearest neighbor (KNN) and back-propagation neural network (BPNN) methods. The SVM method is more suitable for time series predictions of wheat stripe rust. The model obtained accuracy based on the optimal VI combinations and the SVM increased over time; the highest accuracy was 86.2%. These results indicate that the prediction model can provide guidance and suggestions for early disease prevention of the study site, and the method combines time series Sentinel-2 images and the SVM, which can be used to predict wheat stripe rust.

Population Diversity, Dynamics, and Differentiation of Wheat Stripe Rust Pathogen Puccinia striiformis f. sp. tritici From 2010 to 2017 and Comparison With 1968 to 2009 in the United States

Stripe rust, caused by Puccinia striiformis f. sp. tritici (Pst), is a serious disease on wheat in the United States, especially after 2000. In the present study, 2,247 Pst isolates collected over all stripe rust epidemiological regions in the United States from 2010 to 2017 were genotyped at 14 simple sequence repeat (SSR) loci to investigate the population diversity, dynamics, and differentiation. A total of 1,454 multilocus genotypes (MLGs) were detected. In general, the populations in the west (regions 1–6) had more MLGs and higher diversities than the populations in the east (regions 7–12). The populations of 2010 and 2011 were more different from the other years. Genetic variation was higher among years than among regions, indicating the fast changes of the population. The divergence (Gst) was bigger between the west population and east population than among regions within either the west or east population. Gene flow was stronger among the regional populations in the east than in the west. Clustering analyses revealed 3 major molecular groups (MGs) and 10 sub-MGs by combining the genotypic data of 2010–2017 isolates with those of 1968–2009. MG1 contained both 1968–2009 isolates (23.1%) and 2010–2017 isolates (76.9%). MG2 had 99.4% of isolates from 1968–2009. MG3, which was the most recent and distinct group, had 99.1% of isolates from 2010–2017. Of the 10 sub-MGs, 5 (MG1-3, MG1-5, MG3-2, MG3-3, and MG3-4) were detected only from 2011 to 2017. The SSR genotypes had a moderate, but significant correlation (r = 0.325; p < 0.0001) with the virulence phenotype data. The standard index values of association (rbarD = 0.11) based on either regional or yearly populations suggest clonal reproduction. This study indicated high diversity, fast dynamics, and various levels of differentiation of the Pst population over the years and among epidemiological regions, and the results should be useful for managing wheat stripe rust.