Risk-based corrective action (RBCA) is rapidly becoming the method of choic
e for remediating contaminated groundwater. In this paper, a management mod
el is presented that simultaneously predicts risk and proposes cost-effecti
ve options for reducing risk to acceptable levels under conditions of uncer
tainty. The model combines a noisy genetic algorithm with a numerical fate
and transport model and an exposure and risk assessment model. The noisy ge
netic algorithm uses sampling from parameter distributions to assess the pe
rformance of candidate designs. Results from an application to a site from
the literature show that the noisy genetic algorithm is capable of identify
ing highly reliable designs from a small number of samples, a significant a
dvantage for computationally intensive groundwater management models. For t
he site considered, time-dependent costs associated with monitoring and the
remedial system were significant, illustrating the potential importance of
allowing variable cleanup lengths and a realistic cost function.