The paper presents an IoT-based soil pH detection and crop recommendation system designed to enhance agricultural productivity and sustainability. The system integrates IoT-enabled sensors that monitor key soil parameters such as nitrogen, phosphorus, potassium, pH, temperature, and moisture. This data is transmitted to a cloud-based database, where machine learning algorithms (including Linear Regression, K-Nearest Neighbor, Decision Tree, Random Forest Regression, Neural Network, Support Vector Machine, and XGBoost) analyze the information to provide precise crop recommendations. The system aims to optimize fertilizer use, reduce labor, and increase yields by leveraging real-time data and advanced analytics. The project's hierarchical architecture includes sensor nodes, a wireless sensor network, and a cloud infrastructure, ensuring seamless data collection and analysis. The system also identifies soil deficiencies and suggests appropriate fertilizers, enhancing operational efficiency and economic advancement in the agricultural sector. The paper discusses the system's methodology, experimental setup, and results, emphasizing its potential to transform modern agriculture through data-driven decision-making and sustainable practices.The paper presents an IoT-based soil pH detection and crop recommendation system designed to enhance agricultural productivity and sustainability. The system integrates IoT-enabled sensors that monitor key soil parameters such as nitrogen, phosphorus, potassium, pH, temperature, and moisture. This data is transmitted to a cloud-based database, where machine learning algorithms (including Linear Regression, K-Nearest Neighbor, Decision Tree, Random Forest Regression, Neural Network, Support Vector Machine, and XGBoost) analyze the information to provide precise crop recommendations. The system aims to optimize fertilizer use, reduce labor, and increase yields by leveraging real-time data and advanced analytics. The project's hierarchical architecture includes sensor nodes, a wireless sensor network, and a cloud infrastructure, ensuring seamless data collection and analysis. The system also identifies soil deficiencies and suggests appropriate fertilizers, enhancing operational efficiency and economic advancement in the agricultural sector. The paper discusses the system's methodology, experimental setup, and results, emphasizing its potential to transform modern agriculture through data-driven decision-making and sustainable practices.