Hybrid Calorimeter Reconstruction Tools for AI-Driven Optimization​​

The new Electron Ion Collider (EIC) will be a novel machine in the nuclear physics sector and is at the forefront of current technology. With new technology, detector research and development (R&D) becomes ever more important to ensure the machinery is reporting the best results. With artificial intelligence (AI) becoming widespread in many professional fields, AI detector optimization is a logical step for nuclear physics. This project focuses on event reconstruction of the electromagnetic calorimeter located in the electron endcap. This calorimeter will detect scattered electrons that collide with a proton and report the energy, position, and incident angle of the electron. With this data, events are graphically and visually reconstructed. Calorimeter reconstruction methods need to be finished before optimization is started in order to verify the optimized results. With the calorimeter having two different materials, methods need to be developed to analyze the area between the materials. The reconstruction tools were built using JANA2, G4E, and ROOT. These tools are needed for verifying optimization results and future reconstruction analysis of the calorimeter. A form of Bayesian Optimization will be used for detector optimization as well as transition area reconstruction. The reconstruction tools are in place for future AI optimization which will provide better results from the EIC.