GSIF.env
(Package: GSIF) :
GSIF specific environmental variables / paths
Sets the environmental, package specific parameters and settings (URLs, names, default cell size and similar) that can be later on passed to other functions.
as.geosamples
(Package: GSIF) :
Converts an object to geosamples class
Converts an object of class "SoilProfileCollection" or "SpatialPointsDataFrame" to an object of class "geosamples" with all measurements broken into individual records. Geosamples are standardized spatially and temporally referenced samples from the Earth's surface.
A class containing predictions of target soil property at six standard depths following the GlobalSoilMap.net specifications: sd1 = 2.5 cm (0–5), sd2 = 10 cm (5–15), sd3 = 22.5 cm (15–30), sd4 = 45 cm (30–60), sd5 = 80 cm (60–100), sd6 = 150 cm (100–200).
Merges objects of class "SpatialPredictions" or "RasterBrickSimulations" and produces average predictions where the two objects overlap spatially. If the predictions are available at different resolutions, then it downscales all other grids to the smallest grid cell size using bicubic splines (for predictions) i.e. nearest neighbor algorithm (for simulations). Weigths can be passed via the RMSE.l argument, otherwise they will be estimated from validation slot (if objects are of the class "SpatialPredictions").
Generates a command script based on the regression model and variogram. This can then be used to run predictions/simulations by using the pre-compiled binary gstat.exe.
spsample.prob
(Package: GSIF) :
Estimate occurrence probabilities of a sampling plan (points)
Estimates occurrence probabilities as an average between the kernel density estimation (spreading of points in geographical space) and MaxLike analysis (spreading of points in feature space). The output 'iprob' indicates whether the sampling plan has systematically missed some important locations / features, and can be used as an input for geostatistical modelling (e.g. as weights for regression modeling).
Tries to automatically fit a 2D or 3D regression-kriging model for a given set of points (object of type "SpatialPointsDataFrame" or "geosamples") and covariates (object of type "SpatialPixelsDataFrame"). It first fits a regression model (e.g. Generalized Linear Model, regression tree, random forest model or similar) following the formulaString, then fits variogram for residuals usign the fit.variogram method from the gstat package. Creates an output object of class gstatModel-class.
Combines kriging and spline interpolation to speed up the kriging with minimal loss in precision, whilst reducing generation of artifacts. Spline interpolation is implemented via the SAGA GIS function "Multilevel B-Spline Interpolation" (SAGA GIS needs to be installed separately).