eXplainable artificial intelligence applied to algorithms for disruption prediction in tokamak devices

Introduction: This work explores the use of eXplainable artificial intelligence (XAI) to analyze a convolutional neural network (CNN) trained for disruption prediction in tokamak devices and fed with inputs composed of different physical quantities. Methods: This work focuses on a reduced dataset containing disruptions that follow patterns which are distinguishable based on their impact on the electron temperature profile. Our objective is to demonstrate that the CNN, without explicit training for these specific mechanisms, has implicitly learned to differentiate between these two disruption paths. With this purpose, two XAI algorithms have been implemented: occlusion and saliency maps. Results: The main outcome of this paper comes from the temperature profile analysis, which evaluates whether the CNN prioritizes the outer and inner regions. Discussion: The result of this investigation reveals a consistent shift in the CNN’s output sensitivity depending on whether the inner or outer part of the temperature profile is perturbed, reflecting the underlying physical phenomena occurring in the plasma.