fields (version 9.6)

rdist.earth: Great circle distance matrix or vector

Description

Given two sets of longitude/latitude locations, rdist.earth computes the Great circle (geographic) distance matrix among all pairings and rdist.earth.vec computes a vector of pairwise great circle distances between corresponding elements of the input locations using the Haversine method and is used in empirical variogram calculations.

Usage

rdist.earth(x1, x2, miles = TRUE, R = NULL)
rdist.earth.vec(x1, x2, miles = TRUE, R = NULL)

Arguments

x1

Matrix of first set of lon/lat coordinates first column is the longitudes and second is the latitudes.

x2

Matrix of second set of lon/lat coordinates first column is the longitudes and second is the latitudes. If missing x1 is used.

miles

If true distances are in statute miles if false distances in kilometers.

R

Radius to use for sphere to find spherical distances. If NULL the radius is either in miles or kilometers depending on the values of the miles argument. If R=1 then distances are of course in radians.

Value

The great circle distance matrix if nrow(x1)=m and nrow( x2)=n then the returned matrix will be mXn.

Details

Surprisingly the distance matrix is computed efficiently in R by dot products of the direction cosines. Thanks to Qing Yang for pointing this out a long time ago.

See Also

rdist, stationary.cov, fields.rdist.near

Examples

# NOT RUN {
data(ozone2)
out<- rdist.earth ( ozone2$lon.lat)
#out is a 153X153 distance matrix
upper<-  col(out)> row( out)
# histogram of all pairwise distances. 
hist( out[upper])

#get pairwise distances between first 10 and second 10 lon/lat points
x1 = ozone2$lon.lat[1:10,]
x2 = ozone2$lon.lat[11:20,]
dists = rdist.earth.vec(x1, x2)
print(dists)
# }