An integrated simulation-optimization approach for optimal design of petroleum-contaminated groundwater remediation under uncertainty is proposed. Compared to previous approaches, it has 4 advantages as follows: (1)providing a direct and response-rapid bridge between remediation strategies(pumping rates)and remediation performance(contaminant concentrations)through the created surrogates; (2)alleviating the computational cost in the optimization process; (3)providing a satisfaction level that indicates the degree to which the environmental quality standard is satisfied; (4)preventing the formulation of over optimistic and over pessimistic optimization strategies. The approach is applied to a petroleum-contaminated aquifer located in a power plant of Anhui Province for identifying the optimal remediation strategies. The results show that the pumping rates of most wells would decrease under a relaxed standard or longer remediation duration. The increased telescopic index has no serious effect on the optimal remediation strategy.