rgokpred {spm}

Generate spatial predictions using the hybrid method of random forest in ranger and ordinary kriging (RGOK)

Description

This function is to make spatial predictions using the hybrid method of random forest in ranger and ordinary kriging (RGOK).

Usage

rgokpred(
  longlat,
  trainx,
  trainy,
  longlatpredx,
  predx,
  mtry = function(p) max(1, floor(sqrt(p))),
  num.trees = 500,
  min.node.size = NULL,
  type = "response",
  num.threads = NULL,
  verbose = FALSE,
  nmax = 12,
  vgm.args = ("Sph"),
  block = 0,
  ...
)

Arguments

longlat

a dataframe contains longitude and latitude of point samples (i.e., trainx and trainy).

trainx

a dataframe or matrix contains columns of predictive variables.

trainy

a vector of response, must have length equal to the number of rows in trainx.

longlatpredx

a dataframe contains longitude and latitude of point locations (i.e., the centres of grids) to be predicted.

predx

a dataframe or matrix contains columns of predictive variables for the grids to be predicted.

mtry

a function of number of remaining predictor variables to use as the mtry parameter in the randomForest call.

num.trees

number of trees. By default, 500 is used.

min.node.size

Default 1 for classification, 5 for regression.

type

Type of prediction. One of 'response', 'se', 'terminalNodes' with default 'response'. See ranger::predict.ranger for details.

num.threads

number of threads. Default is number of CPUs available.

verbose

Show computation status and estimated runtime.Default is FALSE.

nmax

for local predicting: the number of nearest observations that should be used for a prediction or simulation, where nearest is defined in terms of the space of the spatial locations. By default, 12.

vgm.args

arguments for vgm, e.g. variogram model of response variable and anisotropy parameters. see notes vgm in gstat for details. By default, "Sph" is used.

block

block size. see krige in gstat for details.

...

other arguments passed on to randomForest or gstat.

Value

A dataframe of longitude, latitude, predictions and variances. The variances are produced by OK based on the residuals of rf.

Note

This function is largely based rfokpred. When 'A zero or negative range was fitted to variogram' occurs, to allow OK running, the range was set to be positive by using min(vgm1$dist). In this case, caution should be taken in applying this method, although sometimes it can still outperform IDW and OK.

Author(s)

Jin Li

References

Wright, M. N. & Ziegler, A. (2017). ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R. J Stat Softw 77:1-17. http://dx.doi.org/10.18637/jss.v077.i01.

Examples

## Not run: 
data(petrel)
data(petrel.grid)
rgokpred1 <- rgokpred(petrel[, c(1,2)], petrel[, c(1,2, 6:9)], petrel[, 3],
petrel.grid[, c(1,2)], petrel.grid, num.trees = 500, nmax = 12, vgm.args =
("Sph"))
names(rgokpred1)

## End(Not run)