This paper assesses a deep learning model's capability in detecting rice leaves. Various metrics, including certainty, recall, F1-score, and accuracy, were employed to determine the model's effectiveness in identifying ten different types of leaves in rice: Rice Hispa, Rice Leaf Folder, Rice Mealybug, Rice Gall Midge, Rice Bug, Termite, Stem Borers, Case Worm, Froghopper, and Stalk-Eyed Flies. The model's findings show accurate detection of biotic factors at rates between 93 and 96% for different classes. Despite some classes’ lower performance, the overall model still meets the necessary precision and recall levels, which are crucial for successful biotic factor management. Recall varies from 65 to 77.5%. Deep learning can improve disease detection and control in farming, leading to better sustainability and food security. In the future, recent segmentation techniques and deep learning models can enhance the recognition of rice leaf biotic diseases in leaves.