Transforming Rice Disease Detection: VGG16 CNN for Automated Leaf Disease Classification

about half of the world's population depends on rice as a basic food; but many leaf diseases-including Tungro, Brown Spot, Blast, and Bacterial Blight-threatens its output. Early and accurate diagnosis of these diseases is essential for good crop management since often-manual inspection methods are slow and prone to error. This work uses the VGG16 convolutional neural network (CNN) model to examine automatic categorization of rice leaf diseases. Created from the dataset were training, validation, and testing sets to assess model performance. After training, the model showed remarkable overall accuracy 95% great precision, recall, and F1-scores over all disease categories. The VGG16 model seems to be a useful instrument for improving control and detection of rice leaf disease. Quick diagnosis of disease symptoms allows this automated approach to significantly improve crop management strategies, reduce farmer economic losses, and therefore guarantee food security. The study highlights the opportunities of deep learning technology in agricultural applications, therefore providing the route for more continuous and efficient disease detection methods in rice farming.