lk: Local Ordinary Kriging

In ltsk: Local Time Space Kriging

Local Ordinary Kriging

Description

Function implements ANN based neighbor search, automatic variogram estimation and ordinary Kriging at query locations.

Usage

lk(query, obs, th, xcoord = "x", ycoord = "y", zcoord = "z",  vlen = 15, cl=NULL)

Arguments

query	a data frame containing query spatial locations
obs	a data frame containing spatial locations and observed data
th	a vector, distance threshold for neighbor search
xcoord	a character constant, field name for x coordinate in both query and obs
ycoord	a character constant, field name for y coordinate in both query and obs
zcoord	a character constant, field name for data in obs
vlen	number of bins to compute local spatial variogram
cl	a cluster object for multi-core computing (default number of cores in the PC minue one), 0 means single core

Details

This function implements a local spatial Kriging method for spatial prediction using large data sets. At each location where prediction is required (termed as query point), a conservative distance threshold is used to select neighboring locations from the observed (or sample) data, which has XY coordinates.

A local variogram is used to estimate ordinary Kriging within this neighborhood.

Implementation of the local Kriging requires specifying a distance threshold (th). It is an upper bound within which spatial auto-correlation is believed to exist. The distance threshold may be obtained from variogram estimates or chosen based on prior knowledge of the underlying spatial process. For the given threshold, ANN tree is used to efficiently identify neighbors.

This function does not perform local kriging when the neighborhood contains less than five distinct spatial locations with observed data in the neighborhood. More data points are recommended for robust varioram estimation.

Four variogram models: Gaussian, exponential, spherical and Matern are automatically fit to the empirical variogram. The range parameter is estimated from the first distance lag where the empirical variogram exceeds 80

The estimated range parameter is used to reduce the neighborhood. Only initial neighbors that are spatially correlated with the process at the query point are used in prediction. In case the estimated range is small, indicating a locally weak spatial process, a sample of 10

Field names for geographic coordinates must match between query and observed data frames.

Value

kriging prediction and standard deviation and quality flags.

krig	predictive mean
sigma	predictive standard error
Hs	estimated range
nugget	estimated nugget
psill	estimated partial sill
model	variogram model

where the variogram model are

1	Spherical
2	Gaussian
3	Exponential
4	Matern

Author(s)

Jun chen ([e-mail]) Jin Chen ([e-mail]) Naresh Kumar ([e-mail]) Dong Liang ([e-mail])

See Also

autoKrige in automap

Examples

data(epa_cl)
data(ex)
out <- lk(ex1.grid[1:10,],ex1.data,0.5,cl=0)

ltsk documentation built on Sept. 3, 2023, 1:06 a.m.