Automating Tomato Leaf Disease Diagnosis: Insights from Machine Learning and Deep Learning Approaches

Detection of tomato leaf diseases is essential for early intervention and crop loss reduction, as well as for early diagnosis and treatment of plant diseases. This study evaluates tomato leaf disease detection by comparing traditional machine learning techniques, such as Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Random Forest, with modern deep learning models, such as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and U-Net. The research illustrates how deep learning models, especially CNNs, significantly improve accuracy, precision, recall, and F1 scores in challenging pattern recognition tasks, while evaluating the advantages and disadvantages of different approaches. Technologies currently being explored to improve the accuracy, efficiency, and scalability of disease detection systems include Explainable Artificial Intelligence (XAI), Edge AI, transfer learning, hybrid models, and multimodal data integration. These findings provide a solid foundation for further study and practical implementation by illustrating how machine learning and deep learning methods can significantly improve precision agriculture.