Application of Convoluted Neural Network and Its Architectures for Fungal Plant Disease Detection

Eighty-five percent of the plants are affected by diseases caused by organisms like fungus, bacteria, and virus, which devastate the natural ecosystem. The most common clues provided by the plants affected by fungal diseases are defaming of the plant color. In literature, several traditional rule-based algorithms and normal image processing techniques are used to identify the fungal plant diseases. However, the traditional approach suffers from poor disease identification accuracy. Convoluted neural network (CNN) is one of the potential deep learning neural networks used for image recognition and classification in plant pathology. In this chapter, some of the potential CNN architectures used for plant disease detection like LeNet, AlexNet, VGGNet, GoogLeNet, ResNet, and ZFnet are discussed with the architecture and advantages. The efficiencies achieved by ResNet and ZFNet are found to be good in terms of accuracy and error rate.

Characteristics of powdery mildew and its importance for wheat grown in Poland

Powdery mildew of grasses and cereals (Blumeria graminis) is a fungal plant disease which is caused by species of fungi from the Erysiphaceae order. B. graminis is a biotrophic parasite, biologically diverse parasite with a high degree of specialization in certain host species and with numerous physiological breeds adapted to different varieties of a particular host species. In Poland, powdery mildew of cereals and grasses is recorded every year, and its greatest intensity is in south-eastern and south-western regions. The degree of infestation by B. graminis varies every year. This means that the disease occurs every year, in greater or lesser severity. Therefore, it requires monitoring (harmfulness thresholds) and chemical control practically in every vegetation season. Nowadays, an important role is played by immunological breeding. In breeding programs, resistance genes from wild crop forms, primitive and indigenous varieties are an effective tool. The introduction of effective resistance genes into cultivated varieties is a common procedure used in breeding program.<br />The aim of this study was to describe the fungal disease of plants from the group of powdery mildews caused by <br /> B. graminis as an overview.

Sarcococca Blight: Use of Whole-Genome Sequencing for Fungal Plant Disease Diagnosis

Early and accurate diagnosis of new plant pathogens is vital for the rapid implementation of effective mitigation strategies and appropriate regulatory responses. Most commonly, pathogen identification relies on morphology and DNA marker analysis. However, for new diseases, these approaches may not be sufficient for precise diagnosis. In this study, we used whole-genome sequencing (WGS) to identify the causal agent of a new disease affecting Sarcococca hookeriana (sarcococca). Blight symptoms were observed on sarcococca and adjacent Buxus sempervirens (boxwood) plants in Maryland during 2014. Symptoms on sarcococca were novel, and included twig dieback and dark lesions on leaves and stems. A Calonectria sp. was isolated from both hosts and used to fulfill Koch’s postulates but morphology and marker sequence data precluded species-level identification. A 51.4-Mb WGS was generated for the two isolates and identified both as Calonectria pseudonaviculata. A single-nucleotide polymorphism at a noncoding site differentiated between the two host isolates. These results indicate that the same C. pseudonaviculata genotype has the ability to induce disease on both plant species. This study marks the first application of WGS for fungal plant pathogen diagnosis and demonstrates the power of this approach to rapidly identify causal agents of new diseases.

Asian Soybean Rust

PP-235, a 4-page illustrated fact sheet by Wayne M. Jurick II, Dario F. Narvaez, Carrie L. Harmon, James J. Marois, David L. Wright, and Philip F. Harmon, describes this fungal plant disease new to the US since 2004, its symptoms, causal organism, disease cycle and epidemiology, diagnosis, and management. Includes links to web-based resources and references. Published by the UF Department of Plant Pathology, July 2007.