A Machine Learning Approach for Predicting Plant Diseases and Ensuring Crop Health

Abstract

The widespread prevalence of plant diseases poses significant challenges for the agricultural industry in maintaining crop health and ensuring the continued sustainability of food production. Early detection and accurate diagnosis of such diseases are critical for timely and effective intervention and treatment. Over the last few years, machine learning techniques, specifically Convolutional Neural Networks, have generated promising results in various applications, in particular, computer vision tasks. This paper proposes an innovative method, termed DeepPlantDx, which utilizes CNN algorithms to accurately predict plant diseases and, eventually, afford sustainable crop management strategies. In this paper, we demonstrate effective plant disease diagnosis using convolutional neural networks-based pre-trained models. We focus on hyperparameter tunning of popular pre-trained models, namely DenseNet-121, ResNet-50, VGG-16, and Inception V4. Experiments were performed with the benchmark dataset Plant Village, which contains 54,305 unique image datasets with 38 categories of different plant diseases. Furthermore, the paper analyzes DeepPlantDx's possible impacts such as boosting crop yields, cutting down on the use of pesticides, and promoting sustainable agriculture techniques.