Uncertainty aware machine-learning-based surrogate models for particle accelerators: Study at the Fermilab Booster Accelerator Complex

Surrogate models based on machine learning are increasingly used to accelerate optimization and control of particle accelerators. This paper presents methods for quantifying uncertainties in ML-based surrogate models applied to the Fermilab Booster Accelerator Complex, enabling more reliable predictions and better decision-making.

Physical Review Accelerators and Beams, Volume 26, Article 044602