Machine and Deep Learning Approaches for Plant Disease Detection: A Comprehensive Review

Abstract

People have been using edible foods since ancient times, and they continue to be an essential component of a healthy diet and traditional food systems today. Food crops as a major source of human energy intake, and the challenges they face due to biotic and abiotic stress factors, such as pollution, insects, bacteria, and unfavourable weather conditions. Detecting plant diseases in the early stage is critical for ensuring a stable supply of healthy food, and traditional methods of disease detection by experts are lengthy and have some limitations. The use of Machine and Deep learning is a key aspect of precision farming for crop growth monitoring. Plenty ML strategies, including random forest and support vector machines (SVMs), Convolutional Neural Networks, Deep learning as well as image processing have been used to precisely detect, classify, and predict plant diseases. By leveraging machine learning algorithms, farmers and agricultural experts can accurately detect and diagnose crop diseases, enabling them to take appropriate measures to control and prevent further spread of the disease. This article provides a comprehensive overview of the different AI approaches for plant disease identification and control, drawing on a range of research articles in the field. The application of machine learning in agriculture holds promise for improving crop health and increasing yields and represents an important area of innovation for sustainable agriculture in the future.