A Review on Rice Crop Disease Classification Using Computational Approach

Rice is a significant cereal crop across the world. In rice cultivation, different types of sowing methods are followed, and thus bring in issues regarding sampling collection. Climate, soil, water level, and a diversified variety of crop seeds (hybrid and traditional varieties) and the period of growth are some of the challenges. This survey mainly focuses on rice crop diseases which affect the parts namely leaves, stems, roots, and spikelet; it mainly focuses on leaf-based diseases. Existing methods for diagnosing leaf disease include statistical approaches, data mining, image processing, machine learning, and deep learning techniques. This review mainly addresses diseases of the rice crop, a framework to diagnose rice crop diseases, and computational approaches in Image Processing, Machine Learning, Deep Learning, and Convolutional Neural Networks. Based on performance indicators, interpretations were made for the following algorithms namely support vector machine (SVM), convolutional neural network (CNN), backpropagational neural network (BPNN), and feedforward neural network (FFNN).

Advances in the Role of Dark Septate Endophytes in the Plant Resistance to Abiotic and Biotic Stresses

Endophytic fungi have been studied in recent decades to understand how they interact with their hosts, the types of relationships they establish, and the potential effects of this interaction. Dark septate endophytes (DSE) are isolated from healthy plants and form melanised structures in the roots, including inter- and intracellular hyphae and microsclerotia, causing low host specificity and covering a wide geographic range. Many studies have revealed beneficial relationships between DSE and their hosts, such as enhanced plant growth, nutrient uptake, and resistance to biotic and abiotic stress. Furthermore, in recent decades, studies have revealed the ability of DSE to mitigate the negative effects of crop diseases, thereby highlighting DSE as potential biocontrol agents of plant diseases (BCAs). Given the importance of these fungi in nature, this article is a review of the role of DSE as BCAs. The findings of increasing numbers of studies on these fungi and their relationships with their plant hosts are also discussed to enable their use as a tool for the integrated management of crop diseases and pests.

Natural Products from Medicinal Plants against Phytopathogenic Fusarium Species: Current Research Endeavours, Challenges and Prospects

Many Fusarium species are pathogenic, causing crop diseases during crop production and spoilage of agricultural products in both commercial and smallholder farming. Fusarium attack often results into food contamination, yield loss and increases in food insecurity and food prices. Synthetic fungicides have been used as a control strategy for the management of crop diseases caused by Fusarium pathogens. The negative effects associated with application of many synthetic pesticides has necessitated the need to search for alternative control strategies that are affordable and environmentally safe. Research on medicinal plants as control agents for Fusarium pathogens has received attention since plants are readily available and they contain wide variety of secondary metabolites that are biodegradable. The activities of solvent extracts, essential oils and compounds from medicinal plants have been tested against Fusarium phytopathogenic species. A summary of recent information on antifungal activity of plants against Fusarium species is valuable for the development of biopesticides. This paper reviews the antifungal research conducted on medicinal plants against Fusarium pathogens, over a 10-year period, from January 2012 to May 2021. We also highlight the challenges and opportunities of using natural products from medicinal plants in crop protection. Several databases (Science Direct and Web of Science) were used to obtain information on botanical products used to control Fusarium diseases on crops. Keywords search used included natural products, antifungal, Fusarium, crops diseases, phytopathogenic, natural compounds and essential oil.

Small but mighty: Functional landscape of the versatile geminivirus-encoded C4 protein

The fast-paced evolution of viruses enables them to quickly adapt to the organisms they infect by constantly exploring the potential functional landscape of the proteins encoded in their genomes. Geminiviruses, DNA viruses infecting plants and causing devastating crop diseases worldwide, produce a limited number of multifunctional proteins that mediate the manipulation of the cellular environment to the virus’ advantage. Among the proteins produced by the members of this family, C4, the smallest one described to date, is emerging as a powerful viral effector with unexpected versatility. C4 is the only geminiviral protein consistently subjected to positive selection and displays a number of dynamic subcellular localizations, interacting partners, and functions, which can vary between viral species. In this review, we aim to summarize our current knowledge on this remarkable viral protein, encompassing the different aspects of its multilayered diversity, and discuss what it can teach us about geminivirus evolution, invasion requirements, and virulence strategies.

Identification of Tomato Leaf Diseases Using Deep Convolutional Neural Networks

Crop disease is a major issue now days; as it drastically reduces food production rate. Tomato is cultivated in major part of the world. The most common diseases that affect tomato crops are bacterial spot, early blight, septoria leaf spot, late blight, leaf mold, target spot, etc. In order to increase the production rate of tomato, early identification of diseases is highly required. The existing work contains very less accurate system for identification of tomato crop diseases. The goal of our work is to propose cost effective and efficient deep learning model inspired from Alexnet for identification of tomato crop diseases. To validate the performance of proposed model, experiments have also been done on standard pretrained models. The plantVillage dataset is used for the same, which contains 18,160 images of diseased and non-diseased tomato leaf. The disease identification accuracy of proposed model is compared with standard pretrained models and found that proposed model gave more promising results for tomato crop diseases identification.

Identification of Tomato Leaf Diseases using Deep Convolutional Neural Networks

Crop disease is a major issue now days; as it drastically reduces food production rate. Tomato is cultivated in major part of the world. The most common diseases that affect tomato crops are bacterial spot, early blight, septoria leaf spot, late blight, leaf mold, target spot, etc. In order to increase the production rate of tomato, early identification of diseases is highly required. The existing work contains very less accurate system for identification of tomato crop diseases. The goal of our work is to propose cost effective and efficient deep learning model inspired from Alexnet for identification of tomato crop diseases. To validate the performance of proposed model, experiments have also been done on standard pretrained models. The plantVillage dataset is used for the same, which contains 18,160 images of diseased and non-diseased tomato leaf. The disease identification accuracy of proposed model is compared with standard pretrained models and found that proposed model gave more promising results for tomato crop diseases identification.