Treatment of Epistemic Uncertainty in Environmental Fate Models – Consequences on Chemical Safety Regulatory Strategies

The practical impact of treatment of epistemic uncertainty on decision making was illustrated on two kinds of decisions from chemical regulation. First, regulatory strategies derived from a simplified decision model based on toxicity and persistence showed that regulated level of exposure is more conservative (safe) when uncertainty has been given a non-probabilistic treatment. Persistence and its uncertainty had been assessed by a Level II fugacity model for which input parameters had been quantified either by Bayesian probabilities, fuzzy numbers (non-probabilistic), or combinations of these (probability boxes). These findings are restricted to how we let decision makers respond to uncertainty in model predictions by the chosen set of decision rules. Further, the use of either treatment depends on the quality and quantity of background knowledge and the required level of detail on the assessment. In the absence of experimentally tested physicochemical endpoints, European chemical regulation REACH allows the use of non-testing strategies such as Quantitative Structure-Property Relationships (QSPR) to predict the required information. The second decision problem was to select which chemical substances to prioritize for experimental testing in order to strengthen the background knowledge for chemical regulation with respect to the uncertainty in QSPR predictions. We found that the value of reducing uncertainty, given by the expected gain in net benefit for society, was affected by its treatment and there were no consistent order of testing of the three compounds. However, value of information is a Bayesian probabilistic approach that, unless developed further, loose its interpretability under other treatments of uncertainty. The framework of a predictive model, risk model, decision model and value of information analysis provides a computational template for further evaluation of the effect of treatment of uncertainty on decision making.