A Comprehensive Performance Analysis of Pretrained Transfer Learning Models for Date Palm Disease Classification

Artificial Intelligence (AI) has emerged as a game-changer in the field of agriculture, revolutionizing various aspects of crop management. Among its many applications, disease detection and classification have gained significant attention due to their direct impact on crop health and productivity. This study focuses on a comprehensive performance analysis of six pre-trained deep-learning models specifically designed for a stage-wise classification of white-scale date palm disease (WSD). By evaluating key metrics such as accuracy, sensitivity towards the amount of data used for training, and inference time, the study aims to identify the most effective model for accurately identifying and categorizing different stages of WSD. The results highlight the MobileNet model as the top performer, demonstrating superior accuracy and inference time compared to the other models. Moreover, the MobileNet model achieves high classification accuracy while using only 60% of the data for training. By leveraging the power of deep learning, this study contributes to enhancing disease management practices in date palm agriculture, leading to improved crop yield, reduced losses, and sustainable food production.