Comparison of species sensitivity distributions derived from interspecies correlation models to distributions used to derive water quality criteria

Species sensitivity distributions (SSD) require a large number of measured toxicity values to define a hazard level protective of multiple species. This investigation comprehensively evaluated the accuracy of SSDs generated from toxicity values predicted from interspecies correlation estimation (ICE) models. ICE models are log-log correlations of multiple chemical toxicity values for a pair of species that allow the toxicity of multiple species to be predicted from a single measured acute toxicity value for a surrogate species. ICE SSDs were generated using four surrogate species (fathead minnow, Pimephales promelas; rainbow trout, Oncorhynchus mykiss; sheepshead minnow, Cyprinodon varigatus, and water flea, Daphnia magna). ICE-based hazard concentrations (HC5s) from the 5th percentile of the log-logistic distribution of toxicity values were compared to HC5s determined from the acute toxicity of 55 chemicals from the United States Environmental Protection Agency Ambient Water Quality Criteria (AWQC). Measured fish and invertebrate acute toxicity data and HC5s from the AWQC data sets were compared to ICE-based HC5s. Surrogate species choice was found to be an important consideration in developing predictive HC5s. These results illustrated that fish predict fish better than invertebrates and D. magna predicted invertebrates better than most fish. For example, a mixed model of predicted fish and invertebrates from fathead minnow and D. magna as surrogate species provided predictive relationships with an average factor of 3.0 (+/- 6.7) over 7 orders of toxic magnitude and several chemical classes (HC5predicted/HC5(measured))The application of ICE models is recommended as a valid approach for generating SSDs and hazard concentrations for chemicals with limited toxicity data.