TomOpt: Muon Tomography experiment optimization

• DOI: 10.31526/jais.2024.492
• Publication Date: 2024-04-02T11:20:50Z
• Authors: Lagrange, Maxime; Strong, Giles C; Bordignon, Anna; Bury, Florian; Dorigo, Tommaso; Giammanco, Andrea; Heikal, Mariam; Lamparth, Max; Nardi, Federico; Orio, Aitor; Vischia, Pietro; Zaraket, Haitham
• Keywords: [PHYS]Physics [physics]; machine learning; 500; computer science; [INFO]Computer Science [cs]; [PHYS.PHYS.PHYS-INS-DET]Physics [physics]/Physics [physics]/Instrumentation and Detectors [physics.ins-det]; artificial intelligence; 620

International audience ; The Tomopt software is a tool to optimize the geometrical layout and specifications of detectors designed for muon scattering tomography. Based on differentiable programming techniques, Tomopt consists in a modular pipeline that models all the aspects of a muon tomography task, from the generation and interaction of cosmic ray muons with a parameterized detector and passive material, to the inference on the volume properties. This enables the optimization of the detector parameters via gradient descent, to suggest optimal detector configurations and specifications. This optimisation is subjected to various external constraints such as cost, logistic and material identification efficiency.