Abstract

Soil texture mapping is crucial for precision agriculture, environmental management, and land use planning. Traditional soil sampling methods are time-consuming, expensive, and provide limited spatial coverage. This study presents an innovative approach for predictive soil texture mapping using airborne radiometric data integrated with advanced geospatial modeling techniques. The research demonstrates the application of gamma-ray spectrometry data combined with machine learning algorithms to predict soil texture distributions across heterogeneous landscapes. Results indicate that the integration of potassium (K), uranium (U), and thorium (Th) radiometric channels with digital elevation models and satellite imagery significantly improves soil texture prediction accuracy. The developed methodology achieved an overall accuracy of 87.3% for clay content prediction and 84.6% for sand fraction estimation. This approach offers a cost-effective and spatially comprehensive solution for large-scale soil texture mapping, supporting sustainable agricultural practices and environmental management decisions.