EPJ Web Conf.
Volume 245, 202024th International Conference on Computing in High Energy and Nuclear Physics (CHEP 2019)
|Number of page(s)||9|
|Section||2 - Offline Computing|
|Published online||16 November 2020|
A deep neural network method for analyzing the CMS High Granularity Calorimeter (HGCAL) events
Leprince-Ringuet Laboratory (LLR), Ecole Polytechnique, Palaiseau, France
2 Birla Institute of Technology and Science (BITS), Pilani, India
* e-mail: email@example.com
Published online: 16 November 2020
For the High Luminosity LHC, the CMS collaboration made the ambitious choice of a high granularity design to replace the existing endcap calorimeters. Thousands of particles coming from the multiple interactions create showers in the calorimeters, depositing energy simultaneously in adjacent cells. The data are similar to 3D gray-scale image that should be properly reconstructed. In this paper, we investigate how to localize and identify the thousands of showers in such events with a Deep Neural Network model. This problem is well-known in the “Vision” domain, it belongs to the challenging class: “Object Detection”. Our project shares a lot of similarities with the ones treated in Industry but faces several technological challenges like the 3D treatment. We present the Mask R-CNN model which has already proven its efficiency in Industry (for 2D images). We also present the first results and our plans to extend it to tackle 3D HGCAL data.
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.