Deep Learning-based Identification and Classification of Rice Plant Diseases for Precision Agriculture

Because they reduce both the quality and yield of crops, plant diseases seriously threaten our food supply’s reliability. Plant diseases often result in a significant reduction or complete absence of grain yield in various agricultural contexts. Classifying rice plant diseases and insects pose a significant challenge due to the intricate structure of their composition and the striking resemblance 5bserved among various disease types and insect species. Diseases and insects in crops must be discovered and categorized as soon as possible, ideally before they may spread. There are a number of methods for spotting plant diseases, but deep learning is now the gold standard. The authors provide a novel deep-learning approach for detecting diseases in rice fields using photographs. Convolutional Neural Networks with attention mechanism (CNNAM) can be used to detect diseases in rice plants. Due to its reliability in picture identification and classification, CNNs have been widely employed by researchers for plant disease identification. The identification of rice plant diseases, however, has only been the subject of a small number of studies. This research illuminates the present state of rice plant disease and the methods of disease detection based on Deep Learning. Deep learning models excel about more conventional machine learning methods. With the suggested model, authors were able to categorize rice photos with a 99.8 percent accuracy by learning latent patterns in the raw images.