In this study, we employ an ant colony system (ACS) algorithm, coupled with a threshold accepting technique, to develop an ACS-based hybrid algorithm that is capable of efficiently solving an emergency roadway repair time-space network flow problem. To test how well the algorithm may be applied to actual operations, we perform a case study using data from the 1999 Chi-Chi earthquake in Taiwan. To assess the robustness of the model and solution algorithm for different roadway network patterns, we generate 16 problem instances with four different roadway network patterns. The method that uses CPLEX to directly solve the problem and a previously proposed heuristic are used to compare with our algorithm. The test results show that our algorithm is both effective and efficient enough to solve problems with different roadway networks, and therefore, would be useful in practice.