Soil organic carbon concentration in Eastern Australia

Abstract

This dataset contains measurements related to the depth distribution of organic carbon in soil in Eastern Australia. Soil organic carbon concentration (SOC) was measured to a soil depth of 1 m at 100 sites across NSW, Australia.

Three machine learning algorithms were used to identify predictors important to the model parameters. Multiple regression models were then created based upon the machine learning results using bootstrapped stepwise regressions and the relative importance of the selected variables was assessed using proportional marginal variance decomposition.

Predictor variables used in machine learning algorithms include climate, land-use, site and soil variables.

This dataset is an output of the Importance of Deep Soil Carbon to Long Term Carbon Storage Project which is supported by funding from the Australian Government Department of Agriculture.