Wheat Rust Disease Detection Using Convolutional Neural Network

Abstract

Wheat is one of the major crops of almost all the countries of the world. It contributes a major portion of the world’s food security. Any damage to these crops may impact adversely the food crises of the world. The damage can be because of some diseases like wheat rust. Crop diseases, including wheat rust, are indeed a significant problem affecting food security and agricultural sustainability worldwide. Detecting the health status of crops through technological means can help prevent the spread of diseases more effectively than relying solely on manual labor. The study's focus on wheat rust diseases, including wheat leaf rust, stem rust, and yellow rust, is crucial as these diseases can have varying impacts and levels of damage on crops. By utilizing image analysis of wheat crops, the study aims to differentiate between healthy and infected crops. The experimentation involving various factors such as learning rate, dropout, and train-test split ratio demonstrates the thoroughness of the research. The result shows a 99.64% accuracy rate in detecting wheat rust from healthy crops, which is an impressive outcome, indicating the potential of the developed model to aid in early detection and prevention of wheat rust diseases.