Leaf Nutrient Deficiency Detection Using CNN and IoT Imaging Node

The article showcased an Internet of Things (IoT) image node-integrated CNN-based leaf nutrient deficit detecting system. The suggested system allows for precise, automatic, and real-time tracking of the nutritional status of crops. In the future, we aim to optimise deep learning models for ultralowpower edge devices, integrate multispectral imaging for better nutrient analysis, use data from soil sensors for multimodal modelling, implement federated learning for dispersed farms, and more. Its proctoring has a 90% success rate.

[1]     Y. Chen et al., “Deep Convolutional Networks for Plant Nutrient Deficiency Detection,” IEEE Access, 2023.   [2]      M. Kumar et al., “Advanced CNN Architectures for Agricultural Image Classification,” IEEE Transactions on Artificial Intelligence, 2023.   [3]   L. Zhang et al., “Transfer LearningBased Crop Nutrient Stress Classification,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024.   [4]  R. Patel et al., “IoTBased Smart Agriculture Monitoring System with Vision Module,” IEEE Internet of Things Journal, 2024.   [5]    H. Lee et al., “Edge AI for RealTime Agricultural Image Analysis,” IEEE Access, 2025. [6]      A. Sharma et al., “Explainable AI Techniques for Plant Health Monitoring,” IEEE Transactions on Neural Networks and Learning Systems, 2025.   [7]     T. Nguyen et al., “Lightweight Deep Learning Models for Precision Farming,” IEEE Access, 2026.   [8]  P. Singh et al., “VisionBased Nutrient Stress Detection in Crops,” IEEE Transactions on Artificial Intelligence, 2024. [9]    K. Roy et al., “Smart Farming Systems Using AI and IoT Integration,” IEEE Access, 2025.   [10]  J. Brown et al., “Efficient Deployment of CNN Models on Embedded Agricultural Devices,” IEEE Internet of Things Journal, 2026.