Try this. It works by converting the raster out to a data frame of x,y,value columns, making a spatial points data frame, extracting the missing and non-missing points, fitting on the non-missing points with prediction on the missing points, and then filling in the missing points with the predictions at the missing points in a new raster:
Taking a look at the Kriging tool's documentation I see that "ORDINARY" is not an option for the semi-variogram type in the KrigingModelOrdinary class.
SPHERICAL — Spherical semivariogram model. This is the default.
CIRCULAR — Circular semivariogram model.
EXPONENTIAL — Exponential semivariogram model.
GAUSSIAN — Gaussian (or normal distribution) ...
In the raster calculator (Raster >> Raster Calculator) type:
(vines_layer > grass_layer)*vines
This will filter those values where vines_layer is greater than grass_layer, keeping only those values of vines_layer and NULL values elsewhere, then you may perform your krigging
I don't think you will necessarily BIAS the interpretation or the underlying interpolation - rather you will improve it in areas of closer sampling. Remember that all common interpolation methods are based on getting estimations of the value at points on a regular grid by searching values at original measurement points in the vicinity based on user-specified ...
I would recommend using the lhs package documentation for reference
You would need to install the released version of lhs from CRAN
or via devtools
in your case a example to create a random LHS with 30 samples and 3 variables would be:
X <- randomLHS(30, 3)
Here are a few things I want to point out:
To assign variables you should use the = operator instead of the == operator (which is a comparison operator).
There is no need to specify int nor str.
You can refactor your code as you are assigning 0 and 40 multiple times.
Your code could look something like:
if previousCrop == "Alfalfa: >5 plants/square ...
I'm not sure I fully understand your data, so this might be off the mark. While it is unusual for a variogram to continue to decrease at successively higher lags, it is not impossible.
Consider for example a situation where most of the highest batting averages are concentrated in one area, for example in or around the centre of the city. Lag distances up ...
In the Kriging (e.g. OK) dialogue window, the Variogram Model option (default: a + b * x as shown in your posted picture) requires your direct input of the equation.
Some models (Exp, Sph) use Range, whose input parameters are defined as:
b: Difference between Sill and Nugget (i.e. s-n)
(Note that the meaning of b in the linear ...