Convolutional Neural Networks for Direct Detection of Dark Matter

TL;DR

This paper demonstrates that convolutional neural networks can effectively distinguish dark matter signals from background noise in liquid Xenon detectors, achieving high recall and accuracy in simulated data.

Contribution

The study introduces CNN-based analysis for direct dark matter detection, showing improved event classification without data manipulation.

Findings

CNN achieved 93.4% recall for WIMP events

Precision of 81.2% in distinguishing backgrounds

Overall accuracy of 87.2% in simulations

Abstract

The XENON1T experiment uses a time projection chamber (TPC) with liquid Xenon to search for Weakly Interacting Massive Particles (WIMPs), a proposed Dark Matter particle, via direct detection. As this experiment relies on capturing rare events, the focus is on achieving a high recall of WIMP events. Hence the ability to distinguish between WIMP and the background is extremely important. To accomplish this, we suggest using Convolutional Neural Networks (CNNs); a Machine Learning procedure mainly used in image recognition tasks. To explore this technique we use XENON collaboration open-source software to simulate the TPC graphical output of Dark Matter signals and main backgrounds. A CNN turns out to be a suitable tool for this purpose, as it can identify features in the images that differentiate the two types of events without the need to manipulate or remove data in order to focus on a particular region of the detector. We find that the CNN can distinguish between the dominant background events (ER) and 500 GeV WIMP events with a recall of 93.4\%, precision of 81.2\% and an accuracy of 87.2\%.