Geostatistical analysis as applied to two environmental radiometric time series

This article details the results of an investigation into the application of geostatistical data analysis to two environmentalradiometric time series. The data series employed consist of ⁹⁹Tc values for seaweed (Fucus vesiculosus) and seawater samples taken as part of a marine monitoring program conducted on the coast of northern Norway by the Norwegian Radiation Protection Authority. Geostatistical methods were selected in order to provide information on values of the variables at unsampled times and to investigate the temporalcorrelation exhibited by the data sets. This information is ofuse in the optimisation of future sampling schemes and for providing information on the temporal behaviour of the variablesin question that may not be obtained during a cursory analysis.The results indicate a high degree of temporal correlation withinthe data sets, the correlation for the seawater and seaweed databeing modelled with an exponential and linear function,respectively. The semi-variogram for the seawater data indicatesa temporal range of correlation of approximately 395 days with noapparent random component to the overall variance structure and was described best by an exponential function. The temporal structure of the seaweed data was best modelled by a linear function with a small nugget component. Evidence of drift was present in both semi-variograms. Interpolation of the data setsusing the fitted models and a simple kriging procedure were compared, using a cross-validation procedure, with simple linearinterpolation. Results of this exercise indicate that, for theseawater data, the kriging procedure outperformed the simpleinterpolation with respect to error distribution andcorrelation of estimates with actual values. Using theunbounded linear model with the seaweed data produced estimatesthat were only marginally better than those produced by thesimple interpolation.