TY - JOUR
T1 - Configurable calorimeter simulation for AI applications
AU - Charkin-Gorbulin, Anton
AU - Cranmer, Kyle
AU - Di Bello, Francesco Armando
AU - Dreyer, Etienne
AU - Ganguly, Sanmay
AU - Gross, Eilam
AU - Heinrich, Lukas
AU - Kado, Marumi
AU - Kakati, Nilotpal
AU - Rieck, Patrick
AU - Santi, Lorenzo
AU - Tusoni, Matteo
N1 - We thank Sven Menke for a careful reading of the manuscript. E G would like to thank the United States-Israel BSF, Grant NSF-BSF 2020780, for its support. E D is supported by the Zuckerman STEM Leadership Program. S G is partially supported by Institute of AI and Beyond for the University of Tokyo. K C and P R are supported by NSF award PHY-2111244, and K C is also supported by NSF award OAC-1836650. L H is supported by the Excellence Cluster ORIGINS, which is funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy-EXC-2094-390783311.
PY - 2023/9/5
Y1 - 2023/9/5
N2 - A configurable calorimeter simulation for AI (CoCoA) applications is presented, based on the Geant4 toolkit and interfaced with the Pythia event generator. This open-source project is aimed to support the development of machine learning algorithms in high energy physics that rely on realistic particle shower descriptions, such as reconstruction, fast simulation, and low-level analysis. Specifications such as the granularity and material of its nearly hermetic geometry are user-configurable. The tool is supplemented with simple event processing including topological clustering, jet algorithms, and a nearest-neighbors graph construction. Formatting is also provided to visualise events using the Phoenix event display software.
AB - A configurable calorimeter simulation for AI (CoCoA) applications is presented, based on the Geant4 toolkit and interfaced with the Pythia event generator. This open-source project is aimed to support the development of machine learning algorithms in high energy physics that rely on realistic particle shower descriptions, such as reconstruction, fast simulation, and low-level analysis. Specifications such as the granularity and material of its nearly hermetic geometry are user-configurable. The tool is supplemented with simple event processing including topological clustering, jet algorithms, and a nearest-neighbors graph construction. Formatting is also provided to visualise events using the Phoenix event display software.
UR - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=wis-pure&SrcAuth=WosAPI&KeyUT=WOS:001059977100001&DestLinkType=FullRecord&DestApp=WOS
U2 - 10.1088/2632-2153/acf186
DO - 10.1088/2632-2153/acf186
M3 - مقالة
SN - 2632-2153
VL - 4
JO - Machine Learning: Science and Technology
JF - Machine Learning: Science and Technology
IS - 3
M1 - 035042
ER -