Co‐kriging was used to interpolate values of topsoil 0.5 M NaHCO 3 ‐extractable P at 234 locations in West Sumatra, Indonesia, by exploiting its spatial covariance with a more densely sampled property, 25% HCl‐extractable P. NaHCO 3 ‐P and HCl‐P had been sampled at 52 and 107 locations, respectively, in a nongeometric pattern across the 106 650 has region. Isotropic semivariograms of NaHCO 3 ‐P and HCl‐P and their cross semivariogram showed spatial dependence over 6.3, 4.2, and 10.4 km, respectively, at the sampling scale used. The map of co‐kriged values for NaHCO 3 ‐P showed a similar regional pattern but more local detail than that achieved by kriging from NaHCO 3 ‐P samples alone. Co‐kriging reduced estimation variances (relative to kriging) by up to 40% in areas where sampling density of NaHCO 3 ‐P was lowest. Co‐kriging variances exceeded those of kriging by up to 10% in areas where sampling density of NaHCO 3 ‐P was high. In such areas, the covariate HCl‐P had little effect on the interpolated value but still added a component to the estimation variance. Co‐kriging could not be used to interpolate values for extreme locations where there were no NaHCO 3 ‐P samples within the radius of the kriging neighborhood. Despite local improvement in estimation precision the full benefits of co‐kriging interpolation are not universally obtained from nongeometric variate‐covariate sampling patterns.
No takes yet. Share an insight, caveat, or question.
Trangmar et al. (1986) studied this question.