Gradient-descent-based reconstruction for muon tomography based on automatic differentiation in PyTorch

TL;DR

This paper introduces a novel muon tomography reconstruction method that uses gradient descent and automatic differentiation in PyTorch to optimize material property estimates from muon scattering data.

Contribution

It presents a likelihood-based reconstruction approach leveraging automatic differentiation in PyTorch, offering an alternative to traditional algorithms in muon tomography.

Findings

Demonstrates the feasibility of likelihood-based reconstruction with automatic differentiation.

Shows improved efficiency over conventional methods in initial tests.

Discusses potential advantages of the approach for future applications.

Abstract

Muon scattering tomography is a well-established, non-invasive imaging technique using cosmic-ray muons. Simple algorithms, such as PoCA (Point of Closest Approach), are often utilized to reconstruct the volume of interest from the observed muon tracks. However, it is preferable to apply more advanced reconstruction algorithms to efficiently use the sparse muon statistics that are available. One approach is to formulate the reconstruction task as a likelihood-based problem, where the material properties of the reconstruction volume are treated as an optimization parameter. In this contribution, we present a reconstruction method based on directly maximizing the underlying likelihood using automatic differentiation within the PyTorch framework. We will introduce the general idea of this approach, and evaluate its advantages over conventional reconstruction methods. Furthermore, first reconstruction results for different scenarios will be presented, and the potential that this approach inherently provides will be discussed.