The Light Dark Matter eXperiment

TL;DR

The Light Dark Matter eXperiment (LDMX) is a proposed fixed-target experiment at SLAC aiming to detect sub-GeV dark matter through missing energy and momentum signatures, utilizing advanced machine learning for background discrimination.

Contribution

This paper introduces the design of LDMX and explores innovative machine learning methods to enhance dark matter detection in the low-mass range.

Findings

LDMX detector design tailored for sub-GeV dark matter detection.

Implementation of machine learning techniques like boosted decision trees and graph neural networks.

Strategies for background suppression using calorimeter vetoes.

Abstract

Searching for dark matter (DM) at colliders is one of the biggest challenges in high-energy physics today. Significant efforts have been made to detect DM within the mass range of 1-10,000 GeV at the Large Hadron Collider and other experiments. However, the lower mass range of 0.001-1 GeV remains largely unexplored, despite strong theoretical motivation from thermal dark matter models in that mass range. The Light Dark Matter eXperiment (LDMX) is a proposed fixed-target experiment at SLAC's LCLS-II 8 GeV electron beamline, specifically designed for the direct production of sub-GeV dark matter. The experiment operates on the principle of detecting missing momentum and missing energy signatures. In this talk, we will present the experimental design of LDMX detector and discuss strategies for detecting dark matter. The talk will detail traditional discriminants-based methods using the electromagnetic and hadronic calorimeters as a veto for Standard Model processes. Additionally, the application of advanced machine learning techniques, such as boosted decision trees and graph neural networks, for distinguishing signal from background will be discussed.