Design and Implementation of Smart Agricultural System for Pest Disease Detection in Crops Using Artificial Intelligence

Agriculture plays a vital role in food production and economic stability, yet plant diseases significantly affect crop yield, leading to global losses.Efficient and accurate disease detection is crucial for sustainable farming.This study presents a deep learningbased approach for plant disease detection using a Convolutional Neural Network (CNN).The proposed model incorporates batch normalization, the Adam optimizer with a power-exponential learning rate, and the ReLU activation function to enhance learning efficiency and generalization.A dataset of 70,000 images is utilized for training and evaluation.The model successfully classifies plant leaves as healthy or diseased and identifies specific diseases with an accuracy of 99.4%.Performance metrics such as precision (96.77%) and recall (96%) further validate the robustness of the proposed system.Compared to conventional methods, the integration of advanced optimization techniques improves convergence speed and classification accuracy, making the model highly suitable for real-world agricultural applications.The findings demonstrate the potential of AI-driven smart agricultural systems in early disease detection, enabling timely interventions and improving overall crop health.