10–11 Dec 2025
LNF
Europe/Rome timezone

Development of a Machine Learning Classifier for Deuteron Identification in the GAPS Experiment

Not scheduled
5m
LNF ed.36 - B. Touschek (LNF)

LNF ed.36 - B. Touschek

LNF

288
Show room on map
Physical Poster shown at the Meeting POSTER AND VIDEO UPLOAD

Description

The General Antiparticle Spectrometer (GAPS) is a balloon-borne experiment designed to measure low-energy cosmic-ray antinuclei below 250 MeV/n, aiming to detect indirect signatures of dark matter annihilation or decay. By covering this previously unexplored low-energy region, GAPS will achieve unprecedented sensitivity to antideuteron and antihelium fluxes. The experiment will undertake three long-duration balloon flights over Antarctica, with the first scheduled for the 2025/2026 austral summer. GAPS employs a novel identification method based on the formation, de-excitation, and decay of exotic atoms.
Although the primary focus is on cosmic-ray antinuclei detection, the experiment will also measure abundance of low-energy nuclei such as deuterons. Deuterons, which are plentiful and unaffected by annihilation processes, provide valuable data to refine event identification and to quantify atmospheric effects at flight altitude. To support these aims, advanced machine learning techniques—including deep learning and boosted decision trees—have been applied to develop classifiers capable of discriminating deuterons from the predominant proton and alpha particle backgrounds.

Author

Dr Alessio Tiberio (Università degli Studi di Firenze & INFN)

Presentation materials

There are no materials yet.