Package provides methodology for automated mapping i.e. spatial interpolation and/or prediction using Ensemble Machine Learning (extends functionality of the mlr package). Key functionality includes:
train.spLearner— train a spatial prediction and/or interpolation model using Ensemble Machine Learning (works with numeric, binomial and factor-type variables),
buffer.dist— derive buffer (geographical) distances that can be used as covariates in spLearner,
spc— derive Principal Components using stack of spatial layers,
tile— tile spatial layers so they can be used to run processing in parallel,
spsample.prob— determine inclusion probability / representation of a given point sample based on feature space analysis (maxlike function) and kernel density analysis,
download.landgis— access and download LandGIS layers from www.openlandmap.org,
Warning: most of functions are optimized to run in parallel by default. This might result in high RAM and CPU usage.
Spatial prediction using Ensemble Machine Learning with geographical distances is explained in detail in:
- Hengl, T., MacMillan, R.A., (2019). Predictive Soil Mapping with R. OpenGeoHub foundation, Wageningen, the Netherlands, 370 pages, www.soilmapper.org, ISBN: 978-0-359-30635-0.
- Hengl, T., Nussbaum, M., Wright, M. N., Heuvelink, G. B., and Gräler, B. (2018). Random Forest as a generic framework for predictive modeling of spatial and spatio-temporal variables. PeerJ 6:e5518.