Designing water quality management strategies is often complicated by the difficulty in simultaneously considering large amounts of relevant data, applicable submodels, competing objectives, unquantifiable factors, nonlinear characteristics, and uncertainty during parameterization. Mathematical optimization techniques offer promise in identifying optimal or satisfactory strategies that may be used as benchmarks for decision making. Newer optimization techniques such as genetic algorithm (GA) and fuzzy mathematical programming make the search for optimal control strategies in an uncertain environment more feasible. Using a probabilistic search procedure that emulates Darwinian natural selection, GAs allow multicriteria decision making with respect to both nonlinear feature and fuzzy characteristics to be incorporated directly into the optimization process and generate trade-off curves between cost and environmental quality while identifying good control strategies. This paper verifies such a discovery by a case study of water quality control in the Tseng-Wen river basin in Taiwan.