Analysis of Spectral Reflectance Derived from UAV-Embedded Multispectral and Thermal Sensors as a Function of Soil Moisture Gradient

Abstract. Soil moisture is a key variable for agriculture and environmental management, yet its field measurement remains time-consuming and spatially limited..This study investigated the relationship between gravimetric soil moisture (Ug%) and spectral responses, derived from Unmanned Aerial Vehicle (UAV) mounted multispectral and thermal sensors. The methodology involved acquiring thermal and multispectral imagery over an experimental area with laboratory-identified moisture gradients. An analysis of the importance of moisture predictive variables was performed using machine learning techniques, such as the Random Forest algorithm The Random Forest model achieved R = 0.70 and RMSE = 1.7%, with the thermal band explaining over 50% of the variance, confirming its strong relationship with soil moisture and the ability to distinguish different soil water conditions. The investigation highlighted the importance of precise sensor calibration to ensure the consistency and comparability of data acquired at different times or environmental conditions, a critical factor for analyzing temporal changes and evaluating the effectiveness of management practices.