Improvements to the Australian national soil thickness map using an integrated data mining approach

Abstract

Soil thickness is not easily measured in situ, making it also a challenging variable to reliably map. This study improves on previous digital mapping of soil thickness across Australia using an approach suited to the continent’s unique pedo-geomorphic history. Leveraging three large, in situ observation datasets and a wide range of spatial environmental variables, we developed three models depicting rock outcrops, intermediate and deep soils respectively. Our modelling approach addressed right-censored data, which is a common attribute of soil thickness data, and we applied an iterative, data re-sampling framework to quantify prediction uncertainties. We integrated the three models to create soil thickness maps and associated products of soil thickness exceedance probabilities. Using data excluded from model calibrations, we achieved an overall accuracy of 99% for the binary outcome rock outcrops model, and 85% for the binary outcome deep soils model. Modelling soil thickness of shallow to deep soils resulted in a concordance coefficient of 0.77. Of all the environmental variables considered in this study, those associated with climate data (including topo-climate) were consistently the most often used and important. We associate this finding with the direct and indirect effects of climate on biota and weathering of parental materials along with other factors driving spatial heterogeneity in soil thickness across Australia. While the products generated by this research are not without error, the overall pattern of soil thickness is consistent with previous observations from historical soil surveys across Australia and the results are demonstrably more skilful than previous digital soil mapping efforts.