Electron Energy Regression in the CMS High-Granularity Calorimeter Prototype
This work addresses the problem of efficient event reconstruction for high-energy physics experiments, specifically for the CMS detector at CERN, and is incremental as it applies existing machine learning techniques to new simulated data from a prototype.
The authors tackled the challenge of reconstructing electron energy from a high-granularity calorimeter prototype with 12,000 channels, using machine learning methods to achieve reconstruction from three-dimensional hit energies with known precision.
We present a new publicly available dataset that contains simulated data of a novel calorimeter to be installed at the CERN Large Hadron Collider. This detector will have more than six-million channels with each channel capable of position, ionisation and precision time measurement. Reconstructing these events in an efficient way poses an immense challenge which is being addressed with the latest machine learning techniques. As part of this development a large prototype with 12,000 channels was built and a beam of high-energy electrons incident on it. Using machine learning methods we have reconstructed the energy of incident electrons from the energies of three-dimensional hits, which is known to some precision. By releasing this data publicly we hope to encourage experts in the application of machine learning to develop efficient and accurate image reconstruction of these electrons.