The ion injector complex at CERN supplies ions for collisions at the Large Hadron Collider (LHC) and for fixed-target physics programmes at the Super Proton Synchrotron (SPS) and Proton Synchrotron (PS). In recent years, there has been growing interest in experiments with lighter ions than lead within the ion-physics community. The NA61/SHINE collaboration has requested beams of oxygen, magnesium, and boron for Run 4 (2030-2033), while the HEARTS++ project proposal aims to enable switching between four ion species, with each transition occurring within 15 minutes. Additionally, LHC experiments are considering lighter-than-lead ion beams for Run 5 (2036-2041), pending an assessment of which particle species collisions offer higher nucleon-nucleon luminosity. Consolidating these future scenarios demands an evaluation of the light-ion performance of the present injector complex. This contribution discusses the challenges of the present injector complex in view of light-ion operation and a proposed ion complex upgrade to address future needs.

Modern heavy ion accelerators have become more complex, with greater variability in energy, isotope selection, and A/q ratios. In response, TRIUMF has launched a program focused on automating beam tuning and delivery across its accelerator complex. This initiative includes high-level applications, model-based tuning of the accelerator, and the integration of machine learning tools. For example, Bayesian optimization is used to correct beam orbits within the TRIUMF accelerators. This presentation will provide an overview of the program's progress and highlight some exciting new results achieved over the past two years.

While human operators are very good at finding the optimal conditions that maximize the luminosity in RHIC, maintaining those conditions can be a demanding task. There is also no metric that can measurably determine if those optimal conditions are truly optimal, given the degrees of freedom are very high and there are multiple and competing objectives. In this talk we will describe how we use machine learning and improved physics models to build systems for optimizing the beam brightness during injection at the BNL Booster and AGS synchrotrons and efforts to maintain maximum luminosity in RHIC.

Recent developments of machine-learning-based techniques in RIKEN RI Beam Factory The RIKEN RI Beam Factory (RIBF) is a heavy ion accelerator facility consisting of four ECR ion sources, two linacs, five cyclotrons, and a superconducting fragment separator. For the efficient operation of this facility, developments of beam diagnostics and beam tuning methods using machine learning have been initiated. This presentation will focus on the following two topics. The first is the prediction of the beam intensity from the ECR ion sources. By using plasma images as input to the machine learning model, the beam intensity has been successfully estimated for short-term test datasets. The second is the development of a parameter optimization system based on Bayesian Optimization for high intensity heavy ion beams. We successfully optimized primary 36+Kr beam at 30 enA while monitoring 34+Kr by trackers in a spectrometer. Future prospects for the application of machine learning at RIBF, including these methods, will be discussed.

The heavy ion superconductive linac ALPI has been operating at the Legnaro National Laboratories since its completion in the 1990s. As the first generation in Europe, it featured several innovative techniques and design weaknesses, such as very small transverse and longitudinal acceptances. This led to long setting times and low transmission rates of 35%, compared to 93% obtained using simulations. Additionally, the machine experienced instabilities, requiring frequent accelerator retuning. From 2011 to 2024, an extensive beam dynamics studies program was conducted, culminating in the introduction of Artificial Intelligence techniques in 2022-2024. These techniques made it possible to accelerate the accelerator setup, counteract instabilities and reach the nominal transmission of the linac, about 85%, in June 2024, 32 years after its construction. This paper presents the AI techniques involved, the studies performed, and how they impact routine operations.