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

Recoil-imaging gaseous time projection chambers (TPCs) with directionalsensitivity are attractive for dark matter (DM) searches. Detectors capable ofreconstructing 3D nuclear recoil directions would be uniquely sensitive to thepredicted dipole angular distribution of DM recoils that would unambiguouslyestablish the galactic origin of a claimed DM signal and provide powerfuldiscrimination against background recoils from solar neutrinos. Theseadvantages can only be exploited however, if electron recoil backgrounds fromgamma rays can be sufficiently suppressed. We introduce a deep learning-basedrecoil event classifier that uses a 3D convolutional neural network (3DCNN) toidentify event species based on their recoil images. We compare electronbackground rejection performance of the 3DCNN both to the traditionaldiscriminant of track length, as well as discriminants obtained fromstate-of-the-art shallow learning methods. We train the 3DCNN classifier usingrecoil charge distributions with ionization energies ranging from 0.5-10.5 $\rmkeV_{ee}$, for 25 cm of drift in an 80:10:10 mixture of $\rm He$:$\rmCF_4$:$\rm CHF_3$. The charges are initially segmented into $(100\times100\times 100)$ $\rm\mu m^3$ bins when determining track length and the shallowlearning discriminants, but are rebinned with a reduced segmentation of about$(850\times 850\times 850)$ $\rm\mu m^3$ for the 3DCNN. Despite the courserbinning, compared to using track length, we find that classifying events withthe 3DCNN reduces electron backgrounds by a factor of up to 1,000 andeffectively reduces the energy threshold of our simulated TPC by $30\%$ forfluorine recoils and $50\%$ for helium recoils. We also find that the 3DCNNreduces electron backgrounds by up to a factor of 20 compared to the shallowmachine learning approaches, corresponding to a 2 $\rm keV_{ee}$ reduction inthe energy threshold.

Deep learning for improved keV-scale recoil identification in high resolution gas time projection chambers