Phased sampling for soil remediation

In phased sampling, data obtained in one phase is used to design the sampling network for the next phase. Given N total observations, 1,..., N phases are possible. Experiments were conducted with one-phase, two-phase, and N-phase design algorithms on surrogate models of sites with contaminated soils. The sampling objective was to identify through interpolation, subunits of the site that required remediation. The cost-effectiveness of alternate methods was compared by using a loss function. More phases are better, but in economic terms, the improvement is marginal. The optimal total number of samples is essentially independent of the number of phases. For two phase designs, 75% of samples in the first phase is near optimal; 20% or less is actually counterproductive.