Machine Learning Applied to the Analysis of Nonlinear Beam Dynamics Simulations for the CERN Large Hadron Collider and Its Luminosity Upgrade

A Machine Learning approach to scientific problems has been in use Science and Engineering for decades. High-energy physics provided a natural domain of application Learning, profiting from these powerful tools the advanced analysis data particle colliders. However, applied Accelerator Physics only recently, with several laboratories worldwide deploying intense efforts this domain. At CERN, techniques have beam dynamics studies related Large Hadron Collider its luminosity upgrade, domains including measurements machine performance optimization. In paper, recent applications analyses numerical simulations nonlinear are presented discussed detail. The key concept dynamic aperture provides number topics that selected probe Learning. Indeed, research here aims devise efficient algorithms identify outliers improve quality fitted models expressing time evolution aperture.