Machine-learning techniques applied to three-year exposure of ANAIS-112

TL;DR

This paper applies machine learning, specifically Boosted Decision Trees, to improve noise rejection in the ANAIS-112 dark matter experiment, enhancing sensitivity to potential annual modulation signals over three years.

Contribution

It introduces a novel machine learning-based noise rejection algorithm that significantly reduces background noise in the experiment's low-energy detection range.

Findings

Background noise reduced by nearly 30% between 1-2 keV.

Enhanced sensitivity to annual modulation signals.

Successful reanalysis of three-year data set.

Abstract

ANAIS is a direct dark matter detection experiment aiming at the confirmation or refutation of the DAMA/LIBRA positive annual modulation signal in the low energy detection rate, using the same target and technique. ANAIS-112, located at the Canfranc Underground Laboratory in Spain, is operating an array of 3$\times$3 ultrapure NaI(Tl) crystals with a total mass of 112.5 kg since August 2017. The trigger rate in the region of interest (1-6 keV) is dominated by non-bulk scintillation events. In order to discriminate these noise events from bulk scintillation events, robust filtering protocols have been developed. Although this filtering procedure works very well above 2 keV, the measured rate from 1 to 2 keV is about 50% higher than expected according to our background model, and we cannot discard non-bulk scintillation events as responsible of that excess. In order to improve the rejection of noise events, a Boosted Decision Tree has been developed and applied. With this new PMT-related noise rejection algorithm, the ANAIS-112 background between 1 and 2 keV is reduced by almost 30%, leading to an increase in sensitivity to the annual modulation signal. The reanalysis of the three years of ANAIS-112 data with this technique is also presented.