[R-sig-Geo] Predicting TPS from fields onto SpatialPixelsDataFrame object

[Andy Bunn]

Hi all, I'm used to using gstat for kriging surfaces from either sp or sf and stars objects. E.g., following the workflow below using meuse and meuse.grid. I'm curious how I can use Tps in the fields library. Given the zincTPSModel object below, how can I predict it onto meuse.grid? Thanks in advance, A

library(sp)
library(gstat)
library(fields)

# set up data
data(meuse)
data(meuse.grid)
meuse$logZinc <- log(meuse$zinc)
coordinates(meuse) <- ~x+y
proj4string(meuse) <- CRS("+init=epsg:28992")
coordinates(meuse.grid) <- ~x+y
proj4string(meuse.grid) <- CRS("+init=epsg:28992")
meuse.grid <- as(meuse.grid,"SpatialPixelsDataFrame")

# kriging
zincVar <- variogram(logZinc~1, meuse)
zincVar <- variogram(logZinc~1, meuse)
zincModel <- vgm(psill=0.6, model="Sph", range=750, nugget=0.05)
zincFit <- fit.variogram(object = zincVar, model = zincModel)
plot(zincVar,model=zincModel,pch=20,cex=1.5,col="black",
     ylab=expression("Semivariance ("*gamma*")"),
     xlab="Distance (m)", main = "Zinc concentrations (log(ppm))")
zincKrige <- krige(formula = logZinc~1, locations = meuse, 
                   newdata = meuse.grid, model = zincFit)
spplot(zincKrige,"var1.pred")

# thin plate spline
zincTPSModel <- Tps(coordinates(meuse), meuse$logZinc)
# predict onto meuse.grid?