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

Giles c Strong; Maxime Lagrange; Aitor Orio; Anna Bordignon; Florian Bury; Tommaso Dorigo; Andrea Giammanco; Mariam Heikal; Jan Kieseler; Max Lamparth; Pablo Martínez ruíz del árbol; Federico Nardi; Pietro Vischia; Haitham Zaraket

doi:10.1088/2632-2153/ad52e7

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

Giles c Strong^*, Maxime Lagrange^*, Aitor Orio^*, Anna Bordignon, Florian Bury, Tommaso Dorigo, Andrea Giammanco, Mariam Heikal, Jan Kieseler, Max Lamparth, Pablo Martínez ruíz del árbol, Federico Nardi, Pietro Vischia, Haitham Zaraket

^*Corresponding author for this work

School of Physics

Research output: Contribution to journal › Article (Academic Journal) › peer-review

6 Citations (Scopus)

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 (Strong et al 2024 available at: https://github.com/GilesStrong/tomopt).

Original language	English
Article number	035002
Number of pages	28
Journal	Machine Learning: Science and Technology
Volume	5
Issue number	3
Early online date	3 Jul 2024
DOIs	https://doi.org/10.1088/2632-2153/ad52e7
Publication status	Published - 1 Sept 2024

Bibliographical note

Publisher Copyright:
© 2024 The Author(s). Published by IOP Publishing Ltd.

Access to Document

10.1088/2632-2153/ad52e7Licence: CC BY

Handle.net

Persistent link

Cite this

Strong, G. C., Lagrange, M., Orio, A., Bordignon, A., Bury, F., Dorigo, T., Giammanco, A., Heikal, M., Kieseler, J., Lamparth, M., Martínez ruíz del árbol, P., Nardi, F., Vischia, P., & Zaraket, H. (2024). TomOpt: differential optimisation for task- and constraint-aware design of particle detectors in the context of muon tomography. Machine Learning: Science and Technology, 5(3), Article 035002. https://doi.org/10.1088/2632-2153/ad52e7

@article{6c2ea1a4f48840f6968da491b8ed6c8c,

title = "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 (Strong et al 2024 available at: https://github.com/GilesStrong/tomopt).",

author = "Strong, {Giles c} and Maxime Lagrange and Aitor Orio and Anna Bordignon and Florian Bury and Tommaso Dorigo and Andrea Giammanco and Mariam Heikal and Jan Kieseler and Max Lamparth and {Mart{\'i}nez ru{\'i}z del {\'a}rbol}, Pablo and Federico Nardi and Pietro Vischia and Haitham Zaraket",

note = "Publisher Copyright: {\textcopyright} 2024 The Author(s). Published by IOP Publishing Ltd.",

year = "2024",

month = sep,

day = "1",

doi = "10.1088/2632-2153/ad52e7",

language = "English",

volume = "5",

journal = "Machine Learning: Science and Technology",

issn = "2632-2153",

publisher = "IOP Publishing",

number = "3",

}

Strong, GC, Lagrange, M, Orio, A, Bordignon, A, Bury, F, Dorigo, T, Giammanco, A, Heikal, M, Kieseler, J, Lamparth, M, Martínez ruíz del árbol, P, Nardi, F, Vischia, P & Zaraket, H 2024, 'TomOpt: differential optimisation for task- and constraint-aware design of particle detectors in the context of muon tomography', Machine Learning: Science and Technology, vol. 5, no. 3, 035002. https://doi.org/10.1088/2632-2153/ad52e7

TY - JOUR

T1 - TomOpt

T2 - differential optimisation for task- and constraint-aware design of particle detectors in the context of muon tomography

AU - Strong, Giles c

AU - Lagrange, Maxime

AU - Orio, Aitor

AU - Bordignon, Anna

AU - Bury, Florian

AU - Dorigo, Tommaso

AU - Giammanco, Andrea

AU - Heikal, Mariam

AU - Kieseler, Jan

AU - Lamparth, Max

AU - Martínez ruíz del árbol, Pablo

AU - Nardi, Federico

AU - Vischia, Pietro

AU - Zaraket, Haitham

PY - 2024/9/1

Y1 - 2024/9/1

N2 - 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 (Strong et al 2024 available at: https://github.com/GilesStrong/tomopt).

AB - 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 (Strong et al 2024 available at: https://github.com/GilesStrong/tomopt).

U2 - 10.1088/2632-2153/ad52e7

DO - 10.1088/2632-2153/ad52e7

M3 - Article (Academic Journal)

SN - 2632-2153

VL - 5

JO - Machine Learning: Science and Technology

JF - Machine Learning: Science and Technology

IS - 3

M1 - 035002

ER -

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

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this