Engineers and scientists at Fermilab are designing machine learning programs for the lab’s accelerator complex. These algorithms will enable the laboratory to save energy, give accelerator operators better guidance on maintenance and system performance, and better inform the research timelines of scientists who use the accelerators. The pilot system will used on the Main Injector and Recycler, pictured here. It will eventually be extended to the entire accelerator chain. Photo: Reidar Hahn, Fermilab