Demand uncertainty and variations in user rental-return behavior can lead to an uneven spatial distribution of bicycles, which forces bike-sharing operators to rebalance the bike-sharing system by relocating bicycles from overstocked to understocked stations. In addition, this may lead to increased costs for bike-sharing operators. This paper proposed a two-stage robust model based on spatio-temporal networks to solve the static rebalancing problem in a bike-sharing system affected by demand uncertainty. The model designed a static rebalancing scheme for bike-sharing at a strategic level. To solve the problem, the paper used a customized column-and-constraint generation algorithm. Finally, the effectiveness of the proposed model and algorithm was confirmed using real data from Shanghai, China, providing strategic decision support for the static rebalancing problem in actual bike-sharing systems.