CRCSIBiomass Business (4.12) PhD Project 3.1 – Ultrahigh dimensional variable selection for interpolation of geostatistical data: case studies in soil carbon modelling.
My research focuses on quantifying soil carbon stocks at an individual paddock scale. I am exploring methods to model small numbers of geostatistical observations of soil carbon with broad collections of environmental data all available at much finer spatial resolutions than the soil carbon data. The aim of this modelling is to use these high resolution environmental data to assist the interpolation of the soil carbon observations to full cover maps. I am also interested in visualisation methods to communicate predictions from models, the uncertainty associated with these predictions and the mechanics of the models producing these predictions.
Fitzpatrick, B., Lamb D. W., & Mengersen KL.
(2016). Ultrahigh dimensional variable selection for interpolation of point referenced spatial data: A digital soil mapping case study. PLOS ONE. 11(9), doi: 10.1371/journal.pone.0162489
