Insights into dark matter direct detection experiments: Decision trees versus deep learning

• Autores: Lopez, Daniel Elbio; Perez, Andres Daniel; Ruiz de Austri, Roberto
• Año de publicación: 2025
• Idioma: inglés
• Tipo de recurso: artículo
• Materia: Astropartcile physics; Direct detection dark matter; Machine learning
• Institución: Consejo Nacional de Investigaciones Científicas y Técnicas

The detection of Dark Matter (DM) remains a significant challenge in particle physics. This study exploits advanced machine learning models to improve detection capabilities of liquid xenon time projection chamber experiments, utilizing state-of-the-art transformers alongside traditional methods like Multilayer Perceptrons and Convolutional Neural Networks. We evaluate various data representations and find that simplified feature representations, particularly corrected S1 and S2 signals as well as a few shape-related features including the time difference between signals, retain critical information for classification. Our results show that while transformers offer promising performance, simpler models like XGBoost can achieve comparable results with optimal data representations. We also derive exclusion limits in the cross-section versus DM mass parameter space, showing minimal differences between XGBoost and the best performing deep learning models. The comparative analysis of different machine learning approaches provides a valuable reference for future experiments by guiding the choice of models and data representations to maximize detection capabilities.
Fil: Lopez, Daniel Elbio. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; Argentina. Pontificia Universidad Católica Argentina "Santa María de los Buenos Aires"; Argentina
Fil: Perez, Andres Daniel. Universidad Autónoma de Madrid; España
Fil: Ruiz de Austri, Roberto. Universidad de Valencia; España