Fast and Flexible Analysis of Direct Dark Matter Search Data with Machine Learning

Abstract

We present the results from combining machine learning with the profile likelihood fit procedure, using data from the Large Underground Xenon (LUX) dark matter experiment. This approach demonstrates reduction in computation time by a factor of 30 when compared with the previous approach, without loss of performance on real data. We establish its flexibility to capture non-linear correlations between variables (such as smearing in light and charge signals due to position variation) by achieving equal performance using pulse areas with and without position-corrections applied. Its efficiency and scalability furthermore enables searching for dark matter using additional variables without significant computational burden. We demonstrate this by including a light signal pulse shape variable alongside more traditional inputs such as light and charge signal strengths. This technique can be exploited by future dark matter experiments to make use of additional information, reduce computational resources needed for signal searches and simulations, and make inclusion of physical nuisance parameters in fits tractable.

References in corpus (8)

• Results from a search for dark matter in the complete LUX exposure
• The Large Underground Xenon (LUX) Experiment
• Simultaneous Measurement of Ionization and Scintillation from Nuclear Recoils in Liquid Xenon as Target for a Dark Matter Experiment
• Radiogenic and Muon-Induced Backgrounds in the LUX Dark Matter Detector
• ${}^{83\text{m}}$Kr calibration of the 2013 LUX dark matter search
• 3D Modeling of Electric Fields in the LUX Detector
• Improved Measurements of the \b{eta}-Decay Response of Liquid Xenon with the LUX Detector
• Improved Modeling of $\beta$ Electronic Recoils in Liquid Xenon Using LUX Calibration Data

Cited by in corpus (6)

• Constraints on cosmic-ray boosted dark matter with realistic cross section
• Detector signal characterization with a Bayesian network in XENONnT
• Insights into Dark Matter Direct Detection Experiments: Decision Trees versus Deep Learning
• Bayesian technique to combine independently-trained Machine-Learning models applied to direct dark matter detection
• FlameNEST: Explicit Profile Likelihoods with the Noble Element Simulation Technique
• Suppression of accidental backgrounds with deep neural networks in the PandaX-II experiment