Deep Learning with Jaya Optimization for Accurate and Automated Detection of Paddy Leaf Diseases: Advancing Smart Agriculture through Image Processing and AI-Driven Crop Health Monitoring

Paddy farming plays a vital role in global food security, yet its productivity is severely affected by various leaf diseases, particularly sheath blight, blast, and brown spot. Traditional methods of disease detection, relying on manual observation and laboratory analysis, are time-consuming, error-prone, and unsuitable for large-scale monitoring. This study proposes a deep learning–based framework optimized with the Jaya algorithm for the accurate and automated detection of paddy leaf diseases. The approach leverages convolutional neural networks (CNNs) integrated with image processing techniques to extract discriminative features from leaf samples, ensuring reliable classification across multiple disease categories. To enhance performance, the Jaya optimization algorithm is employed for hyperparameter tuning, thereby improving convergence speed, model precision, and generalization to heterogeneous field conditions. Experimental results indicate that the optimized CNN model achieved an overall classification accuracy of 94.6%, with significant improvements in precision and recall compared to conventional machine learning methods such as KNN, ANN, and SVM. The proposed system is not only computationally efficient but also scalable, making it suitable for real-time deployment using mobile and IoT-enabled platforms. This research contributes to the advancement of smart agriculture by enabling farmers to adopt proactive crop health management strategies, thereby reducing yield losses and promoting sustainable food production.