Towards Sustainable Agriculture: Automated Tomato Leaf Disease Classification using Deep Learning Techniques

Major effects of tomato leaf diseases on world tomato output affect agricultural sustainability including the food security. The early detection of disease like early and late blight as well as leaf mold will help to reduce crop damage and avert major outbreaks. This work aims to build and assess an automated tomato leaf disease categorization CNN model. On utilizing the dataset which consists of 10,000 images which is categorised into ten different images which consists of healthy leaves across the real world environments. The model utilizes the key measures like precision, recall and f1-score which suggests the proposed convolutional neural network model architecture by attaining an accuracy of 95%. With few misclassifications—especially for illnesses like mosaic and healthy leaves—the confusion matrix emphasizes, even more, the amazing success of the algorithm. This work emphasizes how CNNs could support early disease detection, therefore enabling responsible consumption, sustainable agricultural practices, climate resilience, better crop management, and so on. Driving more farmer profitability and higher yields helps to create zero hunger, economic growth, innovation, living on land, and development-oriented alliances.