English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Muon scattering tomography utilises muons, typically originating from cosmicrays to image the interiors of dense objects. However, due to the low flux ofcosmic ray muons at sea-level and the highly complex interactions that muonsdisplay when travelling through matter, existing reconstruction algorithmsoften suffer from low resolution and high noise. In this work, we develop anovel two-stage deep learning algorithm, $\mu$-Net, consisting of an MLP topredict the muon trajectory and a ConvNeXt-based U-Net to convert thescattering points into voxels. $\mu$-Net achieves a state-of-the-artperformance of 17.14 PSNR at the dosage of 1024 muons, outperformingtraditional reconstruction algorithms such as the point of closest approachalgorithm and maximum likelihood and expectation maximisation algorithm.Furthermore, we find that our method is robust to various corruptions such asinaccuracies in the muon momentum or a limited detector resolution. We alsogenerate and publicly release the first large-scale dataset that maps muondetections to voxels. We hope that our research will spark furtherinvestigations into the potential of deep learning to revolutionise this field.

$\mu$-Net: ConvNext-Based U-Nets for Cosmic Muon Tomography