Publication

Abstract : Potato crops are essential to worldwide food safety; however, their cultivation is progressively imperiled by illnesses like early blight and late blight, which lead to significant yield deficiencies. Early identification is indispensable to mitigate these deficiencies, yet conventional strategies are gradual and ineffective, usually missing infections before they become apparent. To address this, we unveil PotatoNet-X, an ingenious hybrid deep learning design that combines Residual Networks (ResNet), DenseNet, and Consideration Mechanisms for precise and effective potato leaf sickness identification. PotatoNet-X leverages these advanced architectures to boost characteristic extraction, improve model generalization, and focus attention on disease-relevant regions of the leaf. The model is prepared and assessed on two freely accessible datasets: PlantVillage and Potato Illness Categorization Dataset (PDCD). PotatoNet-X achieves 98.5% precision and 99% accuracy on the PlantVillage dataset, and 97.79% precision and 98.13% accuracy on the more difficult PDCD dataset. Additionally, the design parses each photo in just 0.045 s, making it perfect for real-time uses in the field. To ensure interpretability, Grad-CAM visualizations are utilized to underscore the areas of the leaf that contribute to illness identification. PotatoNet-X provides a scalable, dependable, and interpretable resolution for early sickness detection in precision agriculture, enabling improved disease management and crop security.