Mapping and monitoring sugarcane crop health is essential for improving yield quality and supporting sustainable agriculture, particularly in Thailand, where sugarcane is an economically important crop. Soil fertility and nutrient availability strongly influence crop productivity; however, traditional soil sampling and laboratory analysis are time-consuming, costly, and limited in spatial coverage. Recent advances in Earth Observation (EO), especially hyperspectral remote sensing, provide new opportunities for large-scale soil monitoring. Hyperspectral data offers detailed spectral information across hundreds of narrow bands, enabling enhanced mapping and monitoring of soil properties (soil moisture, composition, and nutrient status). Hyperspectral data and powerful machine learning algorithms can provide accurate estimations of topsoil parameters across extensive crop field areas. This study mapped and monitored topsoil properties in 2025 in Northeast Thailand sugarcane fields using PRISMA hyperspectral imagery and a random forest (RF) algorithm. Six topsoil nutrients and chemical properties were analyzed, including electrical conductivity (EC), pH, soil organic matter (SOM), nitrogen (N), phosphorus (P), and potassium (K). Field data were collected from 37 sampling plots in March 2025, with 80% used for training and 20% for validation. PRISMA hyperspectral imagery was converted into analysis-ready data using cloud masking and reprojection. Results showed moderate to high performance (R² = 0.30–0.80), with high accuracy for N and SOM nutrient mapping. Spatial maps of the six topsoil nutrients and chemical properties exhibited smooth and consistent distributions for each sugarcane field, highlighting the distribution patterns of soil fertility and supporting sugarcane crop practices. The implemented study workflow was scalable and cost-effective for sustainable sugarcane management monitoring.