Uncertainty Feature Optimization is a framework to cope with optimization problems due to noisy data, using an implicit characterazation of the noise. The Aircraft Scheduling Problem (ASP) is a particular case of such problems, where disruptions randomly perturbate the original flight schedule. This study uses the UFO framework to generate more robust and recoverable schedules, in the sense that more delays are absorbed and when re-optimization is required, the corresponding recovery costs are reduced. We provide computational results for the public data of an European airline provided for the ROADEF Challenge 2009 footnote{\texttt{http://challenge.roadef.or /2009/index.en.htm}}; new schedules are computed with different models, and we compare the a posteriori results obtained by the application of a recovery algorithm.