Techniques for detecting, forecasting, and reducing or avoiding disruptions in fusion devices are described. Data corresponding to operation of a fusion device may be received. Based on the data and one or more
physics-based models, an occurrence of an event and a criticality level of the event may be determined. Based on criticality level of the event, whether a disruption of plasm will occur may be determined. An indication identifying the event and whether the disruption of
plasma in the fusion device will occur may be output to a computing device associated with a user. In some embodiments, based, at least in part, on the criticality level of the first event, a
control system associated with the fusion device may be instructed to perform one or more actions.