Neural Networks for position reconstruction in liquid argon detectors

Abstract

This article explores the integration of Deep Learning and Explainable Artificial Intelligence in Particle Physics, focusing on their application in position reconstruction within dual-phase liquid argon detectors for Dark Matter search. Facing challenges like pile-up scenarios, Neural Networks prove crucial for refining algorithms. This article emphasizes Deep Learning's role in addressing regression and classification problems, such as position reconstruction and particle identification, particularly in Time Projection Chambers. Explainable Artificial Intelligence emerges as pivotal in unraveling Deep Learning's complex decisions, exposing biases, and facilitating improvement cycles. Innovations like Evolutionary Neural Networks and topology-driven dataset reduction offer potential efficiency gains. The conclusion highlights challenges in analyzing massive data volumes, emphasizing the need for adaptability and ethical considerations in the pursuit of understanding Dark Matter.