Image-Based Wheat Fungi Diseases Identification by Deep Learning.

Diseases of cereals caused by pathogenic fungi can significantly reduce crop yields. Many cultures are exposed to them. The disease is difficult to control on a large scale; thus, one of the relevant approaches is the crop field monitoring, which helps to identify the disease at an early stage and take measures to prevent its spread. One of the effective control methods is disease identification based on the analysis of digital images, with the possibility of obtaining them in field conditions, using mobile devices. In this work, we propose a method for the recognition of five fungal diseases of wheat shoots (leaf rust, stem rust, yellow rust, powdery mildew, and septoria), both separately and in case of multiple diseases, with the possibility of identifying the stage of plant development. A set of 2414 images of wheat fungi diseases (WFD2020) was generated, for which expert labeling was performed by the type of disease. More than 80% of the images in the dataset correspond to single disease labels (including seedlings), more than 12% are represented by healthy plants, and 6% of the images labeled are represented by multiple diseases. In the process of creating this set, a method was applied to reduce the degeneracy of the training data based on the image hashing algorithm. The disease-recognition algorithm is based on the convolutional neural network with the EfficientNet architecture. The best accuracy (0.942) was shown by a network with a training strategy based on augmentation and transfer of image styles. The recognition method was implemented as a bot on the Telegram platform, which allows users to assess plants by lesions in the field conditions.

Race Characterization and Molecular Genotyping of Puccinia triticina Populations from Durum Wheat in Russia.

Variability of the Russian population of Puccinia triticina from durum wheat was studied with virulence and simple sequence repeat (SSR) markers. The pathogen was sampled during 2017 to 2019 in all regions with sizable durum wheat (Triticum durum) growing areas from winter (North Caucasus) and spring (Middle Volga, Ural, and West Siberia) wheat. A total of 474 isolates were tested on a set of 20 Lr-gene lines. Molecular genotypes for 105 selected isolates were determined at 11 SSR loci. Variable virulence/avirulence reaction was observed only on three Lr-gene lines, whereas just five SSR loci were polymorphic with two alleles at each. Seven different virulence phenotypes and 11 SSR genotypes were found among 474 and 105 isolates, respectively, indicating a very low variability of the pathogen. One virulence phenotype and three SSR genotypes occurred in all Russian regions. However, two phenotypes were specific to the European regions of Russia (North Caucasus and Middle Volga), while another two were found only in the Asian part of Russia (Ural and West Siberia). Significant differentiation between six populations of P. triticina from durum wheat in the Asian and European (mainly North Caucasus) regions was also shown with numerous metrics and approaches for data with and without clone correction. Relationships among the regional populations of P. triticina from durum wheat established with virulence phenotypes significantly associated with those for SSR genotypes and was similar to the relationships among the regional populations of the pathogen from common wheat.