Development and evaluation of a regression-based model to predict cesium-137 concentration ratios for saltwater fish

Data from published studies and World Wide Web sources were combined to develop a regression model to predict ¹³⁷Cs concentration ratios for saltwater fish. Predictions were developed from 1) numeric trophic levels computed primarily from random resampling of known food items and 2) K concentrations in the saltwater for 65 samplings of 41 species from both the Atlantic and Pacific Oceans. A number of different models were initially developed and evaluated for accuracy, which was assessed as the ratios of independently measured concentration ratios to those predicted by the model. In contrast to freshwater systems where K concentrations are highly variable and are an important factor in affecting fish concentration ratios, the less variable K concentrations in saltwater were relatively unimportant in affecting concentration ratios. As a result the simplest model, which used only trophic level as a predictor, had comparable accuracies to more complex models that also included K concentrations. A test of model accuracy involving comparisons of 56 published concentration ratios from 51 species of marine fish to those predicted by the model indicated that 52 of the predicted concentration ratios were within a factor of 2 of the observed concentration ratios. (author)