Deep Learning Architectures for Accurate and Scalable Nitrogen Deficiency Detection in Rice Plants

Nitrogen deficiency is a major challenge in modern agriculture. This greatly affects the yield and quality of rice cultivation. Early detection and management are important to ensure sustainable production. This study investigates the use of advanced deep-learning techniques to automatically detect nitrogen deficiency in rice plants through image analysis. Convolutional Neural Network (CNN), VGG19, InceptionV3, and InceptionResNetV2-specifically were used and their reliability and accuracy were evaluated. Experimental results show that InceptionResNetV2 had an efficiency of 98.25%, followed by InceptionV3 at 97.50% and VGG19 at 88.50%. This research demonstrates the potential benefits of deep learning in driving change in precision agriculture. It provides an efficient, accurate, and scalable method for crop health monitoring.