TomOpt: Differential optimisation for task- and constraint-aware design of particle detectors in the context of muon tomography

Abstract

We describe a software package, TomOpt, developed to optimise the geometrical layout and specifications of detectors designed for tomography by scattering of cosmic-ray muons. The software exploits differentiable programming for the modeling of muon interactions with detectors and scanned volumes, the inference of volume properties, and the optimisation cycle performing the loss minimisation. In doing so, we provide the first demonstration of end-to-end-differentiable and inference-aware optimisation of particle physics instruments. We study the performance of the software on a relevant benchmark scenario and discuss its potential applications. Our code is available on Github.

V3: Updated to published version; 29 pages content + appendix + refs

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
• Discovery of a big void in Khufu's Pyramid by observation of cosmic-ray muons
• Atmospheric muons as an imaging tool
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• A parametrization of the cosmic-ray muon flux at sea-level
• Material Identification in Nuclear Waste Drums using Muon Scattering Tomography and Multivariate Analysis

Cited by in corpus (5)

• Optimization of a cosmic muon tomography scanner for cargo border control inspection
• Automatic optimisation of a Parallel-Plate Avalanche Counter with Optical Readout
• Fighting Newtonian Noise with Gradient-Based Optimization at the Einstein Telescope
• AI-assisted design of experiments at the frontiers of computation: methods and new perspectives
• ParaFlow: fast calorimeter simulations parameterized in upstream material configurations