Collider experiments probe the fundamental laws of physics by reconstructing particles from collisions, where precise momentum and energy measurements are crucial. The rapid advancements in machine learning (ML), combined with physics domain knowledge, have significantly enhanced reconstruction performance. In this talk, I will review some ML-based studies on improving energy measurements in collider experiments, with a particular focus on hadron calorimeter R&D. I will discuss how ML can enhance hadron energy measurements by leveraging fast timing information from Cherenkov radiation, both with and without traditional scintillation energy measurements. These advancements could potentially open a new direction to the ongoing developments of hadron calorimeters for the next generation of collider experiments.
Yongbin Feng is an Assistant Professor in the Department of Physics and Astronomy at Texas Tech University. He specializes in experimental particle physics, focusing on advanced detector simulations, reconstruction algorithms, and heterogeneous computing, often incorporating machine learning techniques. His research interests include CMS data analyses and the search for dark matter and dark sectors in small fixed-target experiments. Before joining Texas Tech, Dr. Feng was a postdoctoral researcher at Fermilab and completed his Ph.D. at the University of Maryland.