Dark Matter-induced electron excitations in silicon and germanium with Deep Learning

TL;DR

This paper introduces a deep neural network that rapidly predicts dark matter-induced electron excitation rates in silicon and germanium detectors, significantly speeding up calculations for experimental analysis.

Contribution

The authors develop a lightweight deep learning model that accelerates rate calculations by five orders of magnitude, facilitating extensive dark matter parameter scans.

Findings

DNN achieves 5 orders of magnitude speedup over traditional methods

The model simplifies and accelerates dark matter detection rate computations

The neural network is publicly available for use and further research

Abstract

We train a deep neural network (DNN) to output rates of dark matter (DM) induced electron excitations in silicon and germanium detectors. Our DNN provides a massive speedup of around $5$ orders of magnitude relative to existing methods (i.e. QEdark-EFT), allowing for extensive parameter scans in the event of an observed DM signal. The network is also lighter and simpler to use than alternative computational frameworks based on a direct calculation of the DM-induced excitation rate. The DNN can be downloaded $\href{https://github.com/urdshals/DEDD}{\text{here}}$.