A multidimensional linear model for disruption prediction in JET

Abstract

The implementation of Machine Learning (ML) techniques has considerably improved the prediction of

disruptions. However, they usually provide outcomes difficult to understand from a physics point of view due to

their mathematical formulation. In this work an interpretable linear equation has been derived from an accurate ML

disruption predictor. It can be used for real-time forecasting and the off-line analysis of the variables that contribute

to the alarm triggering. To create the linear model, in addition to physic quantities, Time Increments (TIs) have

been considered. TIs represent the variation of two amplitude values of a signal X at two different times divided by

their temporal difference (i.e. ΔX/Δt). To select the best subset of quantities for training purposes among the wide

possible combinations of signals and Tis, Genetic Algorithms have been applied. The results, obtained over an

independent testing database of 131 unintentional disruptive and 1310 non-disruptive shots, are 99,24% of success

rate (94,66% of them with at least 10 ms of warning time) and 3,51% of false alarms.