 This paper proposes a novel approach to assessing the capacity of a road network under demand uncertainty. It uses a sensitivity analysis-based approximation method to reduce the computational burden of repeated capacity loading experiments with random sampling of uncertain parameters. Simulation experiments were conducted to evaluate the reliability of road network capacity and the probability of high congestion for each link under uncertain demand. Results show that the proposed method can accurately estimate the capacity of a road network under demand uncertainty and can be used to identify links with a higher risk of congestion. This article was authored by Zhong Zhigu, Mu Chengdu, Zhenquanzhou, and others.