ataKriging: Area-to-area, area-to-point ordinary Kriging prediciton, cross-validation.

Description

Area-to-area, area-to-point ordinary Kriging prediciton, cross-validation.

Usage

ataKriging(x, unknown, ptVgm, nmax = 10, longlat = FALSE,
    showProgress = FALSE, nopar = FALSE, clarkAntiLog = FALSE)
atpKriging(x, unknown0, ptVgm, nmax = 10, longlat=FALSE,
    showProgress = FALSE, nopar = FALSE)
ataKriging.cv(x, nfold = 10, ptVgm, nmax=10, longlat = FALSE,
    showProgress = FALSE, nopar = FALSE, clarkAntiLog = FALSE)

Value

estimated value of destination area and its variance.

Arguments

x: a discreteArea object: list(areaValues, discretePoints), where areaValues: data.frame(areaId,centx,centy,value) discretePoints: data.frame(areaId,ptx,pty,weight)
unknown: a discreted discreteArea object, or just data.frame(areaId,ptx,pty,weight).
unknown0: for points prediction, data.frame(ptx,pty), one point per row.
nfold: number of fold for cross-validation. for leave-one-out cross-validation, nfold = nrow(x$areaValues).
ptVgm: point scale variogram, ataKrigVgm.
nmax: max number of neighborhoods used for interpolation.
longlat: coordinates are longitude/latitude or not.
showProgress: show progress bar for batch interpolation (multi destination areas).
nopar: disable parallel process in the function even if ataStartCluster() has been called, mainly for internal use.
clarkAntiLog: for log-transformed input data, whether the estimated value should be adjusted(i.e. exponentiation).

References

Clark, I., 1998. Geostatistical estimation and the lognormal distribution. Geocongress. Pretoria, RSA., [online] Available from: http://kriging.com/publications/Geocongress1998.pdf. Goovaerts, P., 2008. Kriging and semivariogram deconvolution in the presence of irregular geographical units. Mathematical Geosciences 40 (1): 101-128. Isaaks, E. H., Srivastava, R. M., 1989. An introduction to applied geostatistics. New York, Oxford University Press. Skøien, J. O. and G. Blöschl, et al., 2014. rtop: an R package for interpolation of data with a variable spatial support, with an example from river networks. Computers & Geosciences 67: 180-190.

Examples

Run this code

# \donttest{
library(atakrig)
library(sf)

## load demo data from rtop package ----
if (!require("rtop", quietly = TRUE)) message("rtop library is required for demo data.")
rpath <- system.file("extdata", package="rtop")
observations <- read_sf(rpath, "observations")
observations$obs <- observations$QSUMMER_OB/observations$AREASQKM

## point-scale variogram ----
obs.discrete <- discretizePolygon(observations, cellsize=1500, id="ID", value="obs")
pointsv <- deconvPointVgm(obs.discrete, model="Exp", ngroup=12, rd=0.75, fig=TRUE)

## cross validation ----
pred.cv <- ataKriging.cv(obs.discrete, nfold=length(observations), pointsv)
names(pred.cv)[6] <- "obs"

summary(pred.cv[,c("obs","pred","var")])
cor(pred.cv$obs, pred.cv$pred)			# Pearson correlation
mean(abs(pred.cv$obs - pred.cv$pred))	# MAE
sqrt(mean((pred.cv$obs - pred.cv$pred)^2))	# RMSE

## prediction ----
predictionLocations <- read_sf(rpath, "predictionLocations")
pred.discrete <- discretizePolygon(predictionLocations, cellsize = 1500, id = "ID")
pred <- ataKriging(obs.discrete, pred.discrete, pointsv$pointVariogram)
# }