Enhanced deep-learning approach to spatiotemporal multi-hit reconstruction with delay-line detectors – new publication in Phys. Rev. Applied
In a recent study published in Phys. Rev. Applied, researchers from FAU, the University of Alabama, and LMU report an enhanced deep learning pipeline that substantially improves spatio-temporal multi-hit reconstruction in Delay-Line Detectors. By integrating cross-channel peak detection and novel, self-sufficient peak matching models, the team demonstrates a superior ability to resolve overlapping signals from particles arriving close in space and time, including the first reported results for triple-hit events. Validated through spatial grid and multiphoton peak benchmarks, these advancements offer a robust framework for high-precision particle correlation experiments in fields ranging from attosecond physics to ultra-cold chemistry.
Read the full article at: https://journals.aps.org/prapplied/abstract/10.1103/4rqm-y1l9