Boosted decision trees approach to neck alpha events discrimination in DEAP-3600 experiment

TL;DR

This paper applies advanced machine learning techniques, specifically Boosted Decision Trees with improvements from Extra Trees and XGBoost, to classify background and signal events in the DEAP-3600 dark matter search experiment, enhancing data analysis capabilities.

Contribution

It introduces an improved BDT-based classification approach tailored for the DEAP-3600 experiment, leveraging recent ML advancements.

Findings

Enhanced discrimination between background and signal events.

Improved classification accuracy over previous methods.

Demonstrated effectiveness of XGBoost in particle physics data analysis.

Abstract

Machine learning (ML) has been widely applied in high energy physics to help the physical community in particle classification and data analysis. Here we describe the application of machine learning to solve the problem of classifying background and signal events for the DEAP-3600 dark matter search experiment (SNOLAB, Canada). We apply Boosted Decision Trees (BDT) algorithm of ML with improvements from Extra Trees and eXtra Gradient Boosting (XGBoost) methods.