Radio Frequency (RF) breakdowns are one of the most prevalent limits in RF cavities for particle accelerators. During a breakdown, field enhancement associated with small deformations on the cavity surface results in electrical arcs. Such arcs lead to beam aborts and if they occur frequently, they can cause irreparable damages on the RF cavity surface.

In this paper, we propose a machine learning strategy to predict the occurrence of breakdowns in CERN’s CLIC accelerating structures. With the rising number of available machine learning algorithms, our approach serves as a guideline to develop data-driven models for failure prediction in RF cavities from scratch.

We discuss state-of-the-art algorithms for data exploration with unsupervised machine learning, breakdown prediction with supervised machine learning, and result validation with explainable-AI. By interpreting model parameters of various approaches, we further address opportunities for reverse engineering of physical properties in the CLIC test bench at CERN for deriving fast, reliable, and simple rule based models.