For the spatial distribution analysis of the production, the geostatistics was used, from the semivariogram
modeling and the creation of kriging maps.
models were fitted to the empirical semivariograms
[gamma](h) using GEOEST (Vieira et al.
For a given distance h, empirical Bayesian kriging uses a semivariogram
(10) model with the following form:
The spatial dependence structure was evaluated by geostatistics, calculating the experimental semivariogram
model (Webster and Oliver 2001) was used to quantify spatial variations in SOCD at all locations sampled using geostatistical methods.
analysis showed that soil pH and EC were moderate spatially dependent.
This was calculated for the stations with available weather data, and subsequently the spatial interpolation was made using the ordinary kriging method (Mello, Lima, Silva, Mello, & Oliveira, 2003) and a spherical semivariogram
model as the function to estimate the values for the entire state.
We considered the semivariogram
range as the distance at which locations become spatially independent.
Resistant and exploratory techniques for use in semivariogram
Split samples suggested that model 4 predicted well, and residual semivariogram
plots did not exhibit spatial autocorrelation.
The geostatistical semivariogram
is used to quantify the differences between sampled data values in the terms of separation distance h.
The ordinary Kriging method using the exponential semivariogram
function was applied to create continuous HSI maps.