Recent Advances in IoT-Based Soil Nutrition and Plant Disease Detection System for Smart Agriculture Using Multi-Layer Stacked Residual Coordinate Boosted Sooty Tern Attention Network: A Systematic Review

Abstract

The integration of Internet of Things (IoT) and deep learning has revolutionized smart agriculture by enabling real-time monitoring, intelligent decision-making, and automated crop management. Soil nutrition analysis and plant disease detection are essential for improving crop productivity, sustainability, and efficient resource utilization. Traditional agricultural practices rely on manual inspection and static analysis, which are often inefficient, time-consuming, and prone to errors. IoT-enabled systems overcome these limitations by continuously monitoring soil and environmental conditions such as moisture, temperature, pH, and nutrient levels through interconnected sensors. These data are analyzed using machine learning and deep learning techniques to optimize fertilizer usage and generate accurate crop recommendations. Recent advances in deep learning architectures, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), residual networks, and attention-based hybrid models, have significantly improved plant disease detection accuracy by automatically learning complex disease patterns from leaf images. This review examines recent developments in IoT-based soil nutrition and plant disease detection systems, focusing on hybrid attention-driven architectures and transformer-based techniques. The findings reveal that integrating IoT with advanced deep learning models enhances classification accuracy, adaptability, and agricultural efficiency. However, challenges related to computational complexity, data dependency, scalability, and real-time deployment remain important areas for future research.