Evaluating the effectiveness of a geostatistical approach with groundwater flow modeling for three-dimensional estimation of a contaminant plume

When assessing the risk from an underground environment that is contaminated by radioactive nuclides and hazardous chemicals and planning for remediation, the contaminant plume distribution and the associated un-certainty from measured data should be estimated accurately. While the release history of the contaminant plume may be unknown, the extent of the plume caused by a known source and the associated uncertainty can be calculated inversely from the concentration data using a geostatistical method that accounts for the temporal correlation of its release history and groundwater flow modeling. However, the preceding geostatistical ap-proaches have three drawbacks: (1) no applications of the three-dimensional plume estimation using concen-tration data from multiple depths in real situations, (2) no constraints for the estimation of the plume distribution, which can yield negative concentration and large uncertainties, and (3) few applications to actual cases with multiple contaminants. To address these problems, the non-negativity constraint using Gibbs sampling was incorporated into the geostatistical method with groundwater flow modeling for contaminant plume esti-mation. This method was then tested on groundwater contamination in the Gloucester landfill in Ontario, Canada, using three-dimensional contaminant transport model and concentration data from multiple depths. The method was applied to three water soluble organic contaminants: 1,4-dioxane, tetrahydrofuran, and diethyl ether. The effectiveness of the proposed method was verified by the general agreement of the calculated plume distributions of the three contaminants with concentration data from 66 points in 1982 (linear correlation co-efficient of about 0.7). In particular, the reproduced peak of 1,4-dioxane corresponding to the large disposal in 1978 was more accurate than the result of preceding minimum relative entropy-based studies. The same peak also appeared in the tetrahydrofuran and diethyl ether distributions approximately within the range of the retardation factor derived from the fraction of organic carbon.