Speakers
Description
Current flavour-tagging algorithms at the LHC rely on reconstructed tracks to capture the signatures of displaced heavy-flavour decays. This approach requires a full track reconstruction, which is computationally expensive and not available at the earliest trigger levels in ATLAS. In this work we explore the potential of hit-based b-tagging, i.e. exploiting raw hit patterns in silicon trackers and calorimeters for heavy-flavour discrimination, without explicit track reconstruction.
The first case we investigate stems from making two forward-looking assumptions. First, that future silicon detectors, beyond the ATLAS ITk upgrade, may feature significantly faster readout speeds, enabling tracker hit information to be accessible already at the earliest trigger stages. Second, that such detectors may provide per-hit timing information with sufficient precision to disentangle pileup and reduce combinatorial confusion. The possible replacement of the two innermost pixel layers, which will take place beyond LHC Run 4, is in the right time-scale for such type of upgrade and we want to investigate if current state-of-the-art b-jet AI/DL algorithms could provide enough discrimination power with only two tracker layers information before tracking is performed. This has a large potential to improve considerably higher-level trigger stages and have a big impact on the discovery of key HL-LHC physics benchmarks featuring heavy-flavour final states, such as double Higgs production.
This use-case also motivates the development of general ML models for hit-based b-tagging, capable of learning directly from raw detector information. Such approaches could recover the displaced-hit signatures of heavy-flavour decays, while bypassing the need for full track reconstruction, thus enabling early and efficient heavy-flavour triggers. More broadly, it opens the question of whether sufficiently expressive architectures can approximate or surpass traditional track-based b-tagging performance by leveraging the full richness of the hit-level data.
On the long-term perspective, this project has two key aspects: the portability to future collider experiments through the implementation in the Open Data Detector available through the A Common Tracking Software infrastructure, and the tight interplay with detector technologies, readout and design, maximizing the connections across various CERN groups.
CERN group/ Experiment
CERN ATLAS Team
| Working area | Area 2: Optimal AI deployment for Online Data Processing |
|---|---|
| Project goals | Explore hit-based flavour tagging assuming future trackers with fast readout and precise timing. The goal is to develop ML models that can recognize heavy-flavour signatures directly from raw hits, enabling early b-tagging at the trigger level without full track reconstruction. |
| Timeline | Year 1: Deployment of first demonstrator of hit-based b-tagging architec- ture using innermost layer hits on ATLAS ITk / ODD geometry Year 2: Study of additional information, such as timing, evaluate model on high-pileup events, model optimization. Year 3: Implementation of an ACTS-based prototype for portability to future collider experiments, full deployment on open-data sets, documen- tation. |
| Available person power | 0.4 FTE |
| Additional person power request | 36 DOCT months |
| Is this an already ongoing activity? | No |
| Indicative hardware resources needs | Dedicated GPU servers: A100/H100 nodes with access for interactive and batch training, can be based on Kubernetes similar to current NGT infrastructure. Disk and Data management: access to fast disk for active training samples (current estimate for Phase-II, full event hit recorded in output xAOD is O(20 MB/event). Ideally accessible via eos, similar to LOCALGROUPDISK storage. |