A soil bulk density pedotransfer function based on machine learning: A case study with the ncss soil characterization database

This paper describes a method to develop a soil bulk density pedotransfer function (PTF) using the Random Forest machine-Learning algorithm with soil and environmental data for the conterminous United States. Complete data from 45,818 horizons were extracted from the National Cooperative Soil Survey (NCSS) soil characterization database and used to calibrate and validate the PTF. Environmental data included surficial materials and hierarchical ecosystem land classifications. The results of a five-fold cross-validation showed that the average root mean squared prediction error (RMSPE) was 0.13 g cm-3, and the mean prediction error (MPE) was -0.001 g cm-3. An illustrative example of a weight-to-area conversion using the PTF was done with soil organic carbon (SOC) stocks. The fitted PTF can be used to fill in data gaps for volumetric assessments, as was done for SOC stock calculations. It could also be used with other international soil datasets if environmental data for surficial materials and ecoregion province can be determined and related to categories present in the United States. The PTF model and the resulting bulk density estimates are available for use under an Open Data license and can be accessed from Harvard Dataverse.