Deep learning for Directional Dark Matter search

TL;DR

This paper introduces a deep learning algorithm using 3D convolutional neural networks to enhance dark matter detection in the NEWSdm experiment, achieving high background rejection and probing new WIMP parameter space regions.

Contribution

It presents the first application of deep 3D CNNs for directional dark matter detection, improving background discrimination in the NEWSdm experiment.

Findings

Achieved $10^4$ background rejection power.

Demonstrated the effectiveness of deep 3D CNNs in signal-background separation.

Probed new regions in WIMP parameter space.

Abstract

We provide an algorithm for detection of possible dark matter particle interactions recorded within NEWSdm detector. The NEWSdm (Nuclear Emulsions for WIMP Search directional measure) is an underground Direct detection Dark Matter search experiment. The usage of recent developments in the nuclear emulsions allows probing new regions in the WIMP parameter space. The directional approach, which is the key feature of the NEWSdm experiment, gives the unique chance of overcoming the "neutrino floor". Deep Neural Networks were used for separation between potential DM signal and various classes of background. In this paper, we present the usage of deep 3D Convolutional Neural Networks to take into account the physical peculiarities of the datasets and report the achievement of the required $10^4$ background rejection power.