Machine learning-based heating detection from pressure measurements in the CERN Large Hadron Collider

Abstract Machine learning models are proposed to successfully detect heating from pressure measurements in synchrotron colliders. These models allow to analyze all the pressure measurements in the time available between two consecutive machine runs. The limits of simple heuristic-based algorithms arsing from noise and non-reproducibility are overcome by the proposed machine learning models. These models were trained, tested, and compared with an heuristic-based base-line approach. In particular, for the case of the CERN Large Hadron Collider (LHC), they reached better performance than base-line algorithms, both in precision and recall scores.