Flavour-tagging, the identification of jets originating from b and c quarks, is a critical component of the physics programme of the ATLAS experiment. Current flavour-tagging algorithms rely on the outputs of “low-level” taggers, which are a mixture of manually optimised, physically informed algorithms and machine learning models. A new approach instead uses a single machine learning model which is trained end-to-end and does not require inputs from existing low-level taggers, leading to reduced overall complexity and enhanced performance. The model uses a Graph Neural Network/Transformer architecture to combine information from a variable number of tracks within a jet in order to simultaneously predict the flavour of the jet, the partitioning of tracks in the jet into vertices, and information about the physical origin of the tracks. The auxiliary training tasks are shown to improve performance, whilst also providing insight into the physics of the jet and increasing the explainability of the model. This approach compares favourably with existing state of the art methods, in particular in the challenging high transverse momenta environment, and for b- vs c-jet discrimination leading to improved c-tagging.
Sam Van Stroud is a postdoctoral researcher at UCL working on the ATLAS experiment. He undertook his High Energy Physics Ph.D. at UCL's Centre for Doctoral Training in Data Intensive Science under the supervision of Tim Scanlon, where he had a prominent role working on charged particle track reconstruction (tracking), jet flavour identification (flavour-tagging) and boosted VH, H->bb. Sam has focussed on improving the tracking and flavour-tagging algorithms at high transverse momenta, in particular using cutting-edge machine learning techniques to enhance performance, simplify workflows and extract additional physics information.
Coffee will be served at 10:30.
M. Girone, M. Elsing, L. Moneta, M. Pierini