Efficient CNN Modeling for Rice Leaf Disease Detection and Interpretation via Feature Maps

This paper presents an efficient convolutional neural network (CNN) framework for rice leaf disease detection and interpretation using feature map visualization. The proposed model is designed to accurately classify multiple rice leaf diseases while maintaining computational efficiency suitable for real-time agricultural applications. Unlike conventional deep learning approaches that operate as black-box systems, this work incorporates feature map analysis to enhance interpretability by highlighting critical regions influencing classification decisions. The model leverages optimized convolutional layers, effective data augmentation, and fine-tuned hyperparameters to improve generalization across diverse environmental conditions. Experimental results demonstrate that the proposed approach achieves an accuracy of 100%, outperforming several existing state-of-the-art models in terms of both performance and efficiency. Furthermore, the integration of visual interpretability provides valuable insights for farmers and agricultural experts, enabling better trust and practical usability. The proposed framework offers a scalable, accurate, and interpretable solution for automated rice leaf disease detection, contributing to the advancement of precision agriculture and intelligent crop management systems.