2024/07/04 by Blekman, Freya, Ploerer, Eduardo, Gautam, Kunal
#future colliders #jet tagging #machine learning #neural networks #strange tagging #transformer
paper · doi:10.17181/rdpqa-jqw85
Jet flavour tagging is crucial in experimental high-energy physics. A tagging algorithm, DeepJetTransformer, is presented, which exploits a transformer-based neural network that is substantially faster to train. The DeepJetTransformer network uses information from particle flow-style objects and secondary vertex reconstruction as is standard for b- and c-jet identification supplemented by additional information, such as reconstructed V0s and K±/π± discrimination, typically not included in tagging algorithms at the LHC. The model is trained as a multiclassifier to identify all quark flavours separately and performs excellently in identifying b- and c-jets. An s-tagging efficiency of 40% can be achieved with a 10% ud-jet background efficiency. The impact of including V0s and K±/π± discrimination is presented. The network is applied on exclusive Z → qq ̄ samples to examine the physics potential and is shown to isolate Z → ss ̄ events. Assuming all other backgrounds can be efficiently rejected, a 5σ discovery significance for Z → ss ̄ can be achieved with an integrated luminosity of 60 nb−1, corresponding to less than a second of the FCC-ee run plan at the Z resonance.