Objective: Test various automated spatial prediction frameworks using 2D, 3D and 2D+T data.
General description: This lecture extends 2D geostatistics (Meuse case study) to 3D soil data (Ebergotzen) and 2D+T time series of meteo measurements (HRtemp). In the first examle (2D) organic carbon is soil is mapped in horizontal space only using GLMs, randomForest and regression trees. In the second example soil sand content is mapped using 3D regression-kriging combined with splines, and in the 3rd example mean daily temperatures are predicted using time-series of MODIS LST images together with some static predictors.
- ch. 8. Spatial interpolation, in Bivand et al. 2008: Applied Spatial Data Analysis with R.
- Hengl, T., Heuvelink, G.B.M., Percec Tadic, M., Pebesma, E., 2011. Spatio-temporal prediction of daily temperatures using time-series of MODIS LST images. Theoretical and Applied Climatology, 107(1-2): 265-277.
- Hengl et al. 2012: Ebergotzen tutorial.