This study proposes a deep learning approach for automated tomato disease detection using the YOLOv8 algorithm. The research aims to improve tomato quality and increase crop yields in Saudi Arabia, where tomato production faces significant yield variations due to diseases. The study enhances an existing RoboFlow dataset, achieving an overall accuracy of 66.67% in disease detection. However, class-specific performance varies, highlighting challenges in differentiating certain diseases. The model's effectiveness is evaluated using precision, recall, and mean Average Precision (mAP) metrics. The YOLOv8 architecture, which includes a backbone, neck, and head components, is detailed, emphasizing its ability to detect objects at multiple scales and its "anchor-free" approach. The experimental results show that while the model performs well in identifying some diseases, there are areas for improvement, particularly in distinguishing between visually similar diseases like blossom end rot and sun-scaled rotation. Future research should focus on addressing data imbalance, exploring alternative architectures, and incorporating disease-specific metrics to enhance the robustness and reliability of the automated tomato disease detection system.This study proposes a deep learning approach for automated tomato disease detection using the YOLOv8 algorithm. The research aims to improve tomato quality and increase crop yields in Saudi Arabia, where tomato production faces significant yield variations due to diseases. The study enhances an existing RoboFlow dataset, achieving an overall accuracy of 66.67% in disease detection. However, class-specific performance varies, highlighting challenges in differentiating certain diseases. The model's effectiveness is evaluated using precision, recall, and mean Average Precision (mAP) metrics. The YOLOv8 architecture, which includes a backbone, neck, and head components, is detailed, emphasizing its ability to detect objects at multiple scales and its "anchor-free" approach. The experimental results show that while the model performs well in identifying some diseases, there are areas for improvement, particularly in distinguishing between visually similar diseases like blossom end rot and sun-scaled rotation. Future research should focus on addressing data imbalance, exploring alternative architectures, and incorporating disease-specific metrics to enhance the robustness and reliability of the automated tomato disease detection system.