Spatial prediction of soil bulk density in Switzerland at 30 m resolution

The soil bulk density (BD) maps were developed using the quantile random forest machine learning algorithm, integrating remotely sensed and derived environmental covariates including terrain, climate, vegetation, and soil properties. The BD maps are provided at a 30-meter spatial resolution for multiple soil depths (0, 30, 60, and 100 cm) in GeoTIFF format. Each map includes the mean predicted bulk density along with associated uncertainty estimates. Units: g/cm³ Other soil property maps for Switzerland including soil organic carbon (SOC), clay, sand, nitrogen, and phosphorus can be downloaded here: https://doi.org/10.5281/zenodo.7821649 The Coarse fragment map for Switzerland can be downloaded from: https://doi.org/10.5281/zenodo.17453998 The soil structure class map for Switzerland can be downloaded from: https://zenodo.org/records/20813089 Gupta, S., Scheper, S., Alewell, C. (2025). Mapping Swiss Soil Bulk Density at 30 m Resolution: Insights from Machine Learning, Environmental Covariates, and National Data. Manuscript submitted to International Journal of Applied Earth Observation and Geoinformation, Accepted.