AI breakthrough speeds up particle collision analysis at world's largest physics lab
Physicists at CERN have deployed a transformer-based AI system that identifies heavy-quark jets 3.5 times more accurately than previous methods, dramatically accelerating the search for rare Higgs boson interactions. The advance signals how machine learning is becoming essential to unlocking discoveries at the Large Hadron Collider—with implications for fundamental physics research funding and computational infrastructure needs.
Originaltitel: Transforming jet flavour tagging at ATLAS
<p>Jet flavour tagging enables the identification of jets originating from heavy-flavour quarks in proton-proton collisions at the Large Hadron Collider, playing a critical role in its physics programmes. This paper presents GN2, a transformer-based flavour tagging algorithm deployed by the ATLAS Collaboration that represents a different methodology compared to previous approaches. Designed to classify jets based on the flavour of their constituent particles, GN2 processes low-level tracking information in an end-to-end architecture and incorporates physics-informed auxiliary training objectives to enhance both interpretability and performance. Its performance is validated in both simulation and collision data. The measured c-jet (light-jet) rejection in data is improved by a factor of 3.5 (1.8) for a 70% b-jet tagging efficiency, compared to the previous algorithm. GN2 provides substantial benefits for physics analyses involving heavy-flavour jets, such as measurements of Higgs boson pair production and the couplings of bottom and charm quarks to the Higgs boson, and demonstrates the impact of advanced machine learning methods in experimental particle physics.</p>