<p>Nitrogen deficiency is a critical stress factor in plants, significantly impacting crop yields in precision agriculture. Early detection of nutrient imbalances, such as inadequate nitrogen levels, is essential for optimizing plant growth and achieving high agricultural productivity. Nitrogen plays a vital role in various plant processes, including the synthesis of chlorophyll, proteins, amino acids, and nucleic acids, all of which are crucial for proper plant development. Deficiency in nitrogen can lead to observable changes in plant morphology, such as reduced leaf number, discoloration, and stunted growth. Recent advancements in imaging technologies have facilitated the development of computer vision-based plant phenomics, enabling rapid, non-invasive, and automated detection of plant stress. In this study, we propose an automated deep learning (DL)-based phenotyping approach to detect and classify nitrogen deficiency in plant leaf images. The method employs EfficientNet-B0, a convolutional neural network (CNN) architecture, to identify and categorize stress symptoms associated with nitrogen insufficiency. The performance of the proposed model was evaluated on two datasets, using key metrics including accuracy, precision, recall, and F1 score. The results show that the EfficientNet-B0 model achieves an accuracy of 97.9%, outperforming the baseline model, which reached an accuracy of 93.2%. These results demonstrate the effectiveness of the proposed deep learning model in accurately detecting nitrogen deficiency in plants, offering a promising tool for precision agriculture applications.</p>