We model the value of environmental research in the presence of uncertainty about the sources of environmental pollutants and natural processes affecting the level of pollution. The model may be used to estimate the value of environmental research directed at resolving the uncertainty. We illustrate the model using a numerical simulation of a hypothetical case involving nutrient pollution of coastal waters. We show that the ex ante value of research is positively related to the level of uncertainty. There is a diminishing return with respect to the level of research investment. We find that research is more valuable ex post if it leads to unexpected findings.