Controlling water cycles, anticipating disasters, and enhancing agriculture depends on accurate soil moisture understanding. To address climate-related challenges, precise and real-time measurements from soil moisture sensors are essential. Radio Frequency (RF) soil moisture sensors are wireless, low-cost, and simple devices that revolutionize agriculture with real-time accuracy, advance environmental science, and promote sustainable resource management. This study aims to calibrate an innovative chip-based RF sensor using the gravimetric method for moisture content detection. Sensor calibration will be performed for sandy and loamy soils, as varying soil types affect the dielectric constant and complex permittivity measured by RF sensors. The project will explore linear and polynomial regression machine learning techniques to improve the accuracy, efficiency, and reliability of the calibration curves. A pot test with sandy and loamy soils will validate the sensor for moisture content monitoring by comparing it with a commercial moisture content device. The detection range of the sensor is calibrated and validated up to 35% moisture content. This research can demonstrate the accuracy, simplicity, affordability, and robustness of the chip-based RF sensor for soil moisture detection, contributing to the improvement of precision agricultural enhancements.
