AbstractPower infrastructure is essential for the operation of almost all other critical infrastructure systems, including water, transportation, and telecommunications. Recently, there has been an increase in forced power outage frequency and extent due to infrastructure aging, extreme weather events, and deliberate attacks. To combat forced power outage risks, researchers have been focusing on improving the resilience of different power infrastructure systems. A key aspect of infrastructure resilience is the rapidity, defined as the time required to return to normal operation levels following functionality disruptions. This study developed a machine learning–based framework to predict the rapidity of power infrastructure following forced outages. The framework includes classification models such as bagging, random forests, and artificial neural networks to accommodate the categorical nature of typical power infrastructure component outage features. The framework also includes a genetic algorithm for optimized selection of such features in order to facilitate the model’s best prediction performance. The utility of the developed framework was demonstrated using actual transmission line forced outages data. Within the demonstration application, rapidity was split into two classes indicating short and extended outages, and the random forest classification model had the best rapidity prediction performance. In addition, the influence of key features on outage classification was explored using partial dependence analysis. Finally, insights for resilience-guided asset management were presented. The developed framework enables infrastructure stakeholders to predict forced outage rapidity classes soon after the occurrence of the former—subsequently enabling rapid identification of appropriate resources needed to promptly restore infrastructure functionality and thus ensuring infrastructure resilience.