Powdery mildew is a highly destructive winter wheat pathogen in China. Since the causative agent is sensitive to changing weather conditions, we analyzed climatic records from regions with previous wheat powdery mildew epidemics (1970 to 2012) and investigated the long-term effects of climate change on the percent acreage (PA) of the disease. Then, using PA and the pathogen’s temperature requirements, we constructed a multiregression model to predict changes in epidemics during the 2020s, 2050s, and 2080s under representative concentration pathways RCP2.6, RCP4.5, and RCP8.5. Mean monthly air temperature increased from 1970 to 2012, whereas hours of sunshine and relative humidity decreased (P < 0.001). Year-to-year temperature changes were negatively associated with those of PA during oversummering and late spring periods of disease epidemics, whereas positive relationships were noted for other periods, and year-to-year changes in relative humidity were correlated with PA changes in the early spring period of disease epidemics (P < 0.001). Our models also predicted that PA would increase less under RCP2.6 (14.43%) than under RCP4.5 (14.51%) by the 2020s but would be higher by the 2050s and 2080s and would increase least under RCP8.5 (14.37% by the 2020s). Powdery mildew will, thus, pose an even greater threat to China’s winter wheat production in the future.

Wheat stripe rust (WSR) is a foliar disease that causes destructive damage in the wheat production context. Accurately estimating the severity of WSR in the autumn growing stage can help to objectively monitor the disease incidence level of WSR and predict the nationwide disease incidence in the following year, which have great significance for controlling its nationwide spread and ensuring the safety of grain production. In this study, to address the low accuracy and the efficiency of disease index estimation by traditional methods, WSR-diseased areas are segmented based on Segformer, and the macro disease index (MDI) is automatically calculated for the measurement of canopy-scale disease incidence. The results obtained with different semantic segmentation algorithms, loss functions, and data sets are compared for the segmentation effect, in order to address the severe class imbalance in disease region segmentation. We find that: (1) The results of the various models differed significantly, with Segformer being the best algorithm for WSR segmentation (rust class F1 score = 72.60%), based on the original data set; (2) the imbalanced nature of the data has a significant impact on the identification of the minority class (i.e., the rust class), for which solutions based on loss functions and re-weighting of the minority class are ineffective; (3) data augmentation of the minority class or under-sampling of the original data set to increase the proportion of the rust class greatly improved the F1-score of the model (rust class F1 score = 86.6%), revealing that re-sampling is a simple and effective approach to alleviating the class imbalance problem. Finally, the MDI was used to evaluate the models based on the different data sets, where the model based on the augmented data set presented the best performance (R² = 0.992, RMSE = 0.008). In conclusion, the deep-learning-based semantic segmentation method, and the corresponding optimization measures, applied in this study allow us to achieve pixel-level accurate segmentation of WSR regions on wheat leaves, thus enabling accurate assessment of the degree of WSR disease under complex backgrounds in the field, consequently providing technical support for field surveys and calculation of the disease level.

This study aimed to identify and assess vegetation indices (VIs) and their optimal band combinations using unmanned aerial vehicle (UAV) hyperspectral imagery for the quantitative inversion of wheat stripe rust. This would offer guidance for selecting rust-resistant phenotypes and facilitate large-scale disease monitoring using aerial and spaceborne remote sensing images. The experimental design encompassed 960 wheat varieties (strains) in agricultural fields. Hyperspectral imagery was acquired at 100m altitude during different disease stages, and disease index (DI) was investigated per plot. A custom program explored VIs with two, three, and four bands using 30 calculation methods and 3,463,790 band combinations. Regression models employed three-fold cross-validation and multilayer perceptron (MLP) algorithms, with the mean R ² value indicating optimal index and band combinations. The results revealed that the chosen VIs were effective in inverting the DI. Selected two-band VIs included MGRVI (531, 571), with R ² =0.746±0.01618; the optimal three-band VIs was ARI2 (531, 550±10, 640±25), with R ² =0.755±0.00896; and the best four-band VIs was DBSI (531, 551, 750, 799), with R ² =0.778±0.01300, which was comparable to full-band modeling (R ² =0.775±0.01508). The models’ performance improved with an increasing number of bands in the VIs. This study demonstrated that appropriate multi-VIs modeling enhances performance compared to single-VIs modeling, e.g., six combinations of VIs achieved R ² =0.790±0.01141. These findings underscore the potential of integrating machine learning algorithms and vegetation indices for quantifying wheat rust diseases, laying the foundation for developing airborne and spaceborne imaging sensors for large-scale wheat rust monitoring.

Powdery mildew, caused by Blumeria graminis f. sp. tritici (Bgt), is one of the most damaging diseases to wheat in the world. The cultivation of resistant varieties of wheat is essential for controlling the powdery mildew epidemic. Wheat landraces are important resources of resistance to many diseases. Mapping powdery mildew resistance genes from wheat landraces will promote the development of new varieties with disease resistance. The Chinese wheat landrace Baiyouyantiao possesses characteristic of disease resistance to powdery mildew. To identify the resistance gene in this landrace, Baiyouyantiao was crossed with the susceptible cultivar Jingshuang 16 and seedlings of parents and F₁, BC₁, F₂, and F_2:3 were tested with Bgt isolate E09. The genetic results showed that the resistance of Baiyouyantiao to E09 was controlled by a single recessive gene, tentatively designated PmBYYT. An Illumina wheat 90K single-nucleotide polymorphism (SNP) array was applied to screen polymorphisms between F₂-resistant and F₂-susceptible DNA bulks for identifying the chromosomal location of PmBYYT. A high percentage of polymorphic SNPs between the resistant and susceptible DNA bulks was found on chromosome 7B, indicating that PmBYYT may be located on this chromosome. A genetic linkage map of PmBYYT consisting of two simple sequence repeat markers and eight SNP markers was developed. The two flanking markers were SNP markers W7BL-8 and W7BL-15, with genetic distances of 3 and 2.9 cM, respectively. The results of this study demonstrated the rapid characterization of a wheat disease resistance gene and SNP marker development using the 90K SNP assay. The flanking markers of gene PmBYYT will benefit marker-assisted selection (MAS) and map-based cloning in breeding wheat cultivars with powdery mildew resistance.