A Survey of Methods and Architectures for IoT-Based Soil Nutrition and Plant Disease Detection System for Smart Agriculture Using Multi-Layer Stacked Residual Coordinate Boosted Sooty Tern Attention Network

Abstract

The integration of Internet of Things (IoT) and Artificial Intelligence (AI) has significantly transformed modern agriculture by enabling intelligent monitoring of soil nutrients and early detection of plant diseases. Traditional practices relying on manual inspection often lead to delayed diagnosis, inefficient fertilizer use, and reduced crop yield. Recent advancements in deep learning and optimization techniques have introduced automated, data-driven solutions for precision agriculture. This survey reviews methods and architectures for IoT-based soil nutrition monitoring and plant disease detection, focusing on models such as Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), hybrid CNN-LSTM approaches, and optimization techniques. It highlights a novel Multi-Layer Stacked Residual Coordinate Boosted Sooty Tern Attention Network that combines residual learning and attention mechanisms to improve feature extraction and classification accuracy. IoT systems collect real-time data on soil and environmental conditions, enabling informed decision-making. Hybrid AI models demonstrate superior performance in detection and resource optimization. However, challenges such as computational complexity, data dependency, scalability, and energy constraints remain, emphasizing the need for efficient and scalable solutions.