Plant Disease Prediction using Machine Learning: A Comprehensive Review

Plant diseases have severely affected agricultural yields, causing significant economic losses. To address this, advanced technologies like Machine Learning (ML), Deep Learning (DL), and the Internet of Things (IoT) are being leveraged for early disease detection. This study evaluates ML and DL techniques, including Convolutional Neural Networks (CNNs), support vector machine (SVM), Logistic regression (LR) and transfer learning techniques for plant disease prediction. While DL models excel in processing complex image data, they demand extensive labelled datasets and computational power. Traditional ML approaches, though less resource-heavy, often face limitations in feature extraction and accuracy. The findings highlight the trade-offs between model performance and resource requirements, offering insights for optimizing disease detection in agriculture.