Optimizing Tomato Crop Health: Disease Detection with

Good control depends on accurate and fast identification of tomato leaf diseases since it drastically reduces crop output and quality. This paper uses a deep learning approach employing the ResNet50 model to classify ten forms of tomato leaf diseases: Tomato Mosaic Virus, Target Spot, Bacterial Spot, Tomato Yellow Leaf Curl Virus, Late Blight, Leaf Mold, Early Blight, Two-Spotted Spider Mite, and Septoria Leaf Spot. Trained to differentiate between healthy and unhealthy leaves, a dataset of 10,000-labeled images split into 8,000 for training and 2,000 for testing Celebrated for its accuracy, the ResNet50 model with its deep architecture and residual learning powers reaches an amazing $94 \%$ in disease categorization. This study shows how well ResNet50 improves early disease detection and classification accuracy. Great performance of the model is shown by tests including F1- score and confusion matrix analysis, therefore demonstrating its capacity to promote environment friendly agricultural practices and enhance crop management strategies. The results show the considerable worth artificial neural networks have in conquering major obstacles in plant disease monitoring and control.