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 significantly advanced smart agriculture by enabling real-time monitoring, intelligent decision-making, and automated crop management. Soil nutrition analysis and plant disease detection are crucial for improving crop yield and sustainability, yet traditional methods relying on manual inspection are often time-consuming and error-prone. IoT-based systems address these limitations by continuously collecting data on soil moisture, temperature, pH, and nutrient levels, while deep learning models analyse this data to provide accurate recommendations and optimize fertilizer usage. Recent developments in architectures such as Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and attention-based hybrid models have further improved disease detection accuracy by extracting complex features from plant images. This review examines recent advancements in IoT-enabled soil monitoring and plant disease detection, focusing on hybrid models like multi-layer stacked residual and attention-based networks. It highlights trends, methodologies, and challenges identified in recent studies, emphasizing improved performance through model integration. However, issues such as computational complexity, data dependency, and real-time deployment remain key challenges, suggesting future research in lightweight models and edge computing solutions.