The integration of smart sensors and machine learning technologies for enhanced soil health monitoring has emerged as a game-changer in precision agriculture, providing farmers with data- This study explores the use of advanced technologies such as edge computing, Geographic Information Systems (GIS), Bosch BME280 sensors, Narrowband IoT (NB IoT), and Gradient Boosting Machines (GBMs) to enhance soil management practices. Edge computing enables real-time data processing at the sensor level, allowing for immediate decisions on irrigation, fertilization, and soil treatments. GIS creates detailed spatial maps to visualize soil variability and apply targeted interventions. The Bosch BME280 sensors measure temperature, humidity, and pressure, providing essential data for soil assessments. NB IoT facilitates efficient, low-energy transmission of sensor data across large agricultural areas. The integration of GBMs allows for advanced pattern recognition and predictive analysis, improving forecasts of soil conditions and crop performance. The study shows significant improvements in soil management, with a 15% increase in soil moisture retention, a 10% reduction in irrigation water usage, and a 12% boost in overall crop yield. Soil electrical conductivity was measured with 95% accuracy, optimizing nutrient management. Additionally, the system consistently monitored soil pH and organic carbon levels, with deviations of only 0.05% and 0.1% from target values. These findings highlight the transformative potential of smart sensors and machine learning in precision agriculture, promoting more effective and sustainable farming practices.