2021 Volume 16 Pages 1402073
Prediction and likelihood identification of high-beta disruption in JT-60U has been discussed by means of feature extraction based on sparse modeling. In disruption prediction studies using machine learning, the selection of input parameters is an essential issue. A disruption predictor has been developed by using a linear support vector machine with input parameters selected through an exhaustive search, which is one idea of sparse modeling. The investigated dataset includes not only global plasma parameters but also local parameters such as ion temperature and plasma rotation. As a result of the exhaustive search, five physical parameters, i.e., normalized beta βN, plasma elongation κ, ion temperature Ti and magnetic shear s at the q = 2 rational surface, have been extracted as key parameters of high-beta disruption. The boundary between the disruptive and the non-disruptive zones in multidimensional space has been defined as the power law expression with these key parameters. Consequently, the disruption likelihood has been quantified in terms of probability based on this boundary expression. Careful deliberation of the expression of the disruption likelihood, which is derived with machine learning, could lead to the elucidation of the underlying physics behind disruptions.
