1 minute read
Task 3.7: L1 scouting data compression for efficient data acquisition and anomaly detection

Task leads: Jennifer Ngadiuba (Fermilab)
L1 scouting provides the possibility for unbiased HL-LHC data acquisition and storage for future analysis, but the resulting datasets would be prohibitively large, order 100-1000 PB per data-taking year depending on the kind of information saved. In this task, we propose to apply cutting-edge compression techniques, including nonlinear lossy compression with AI algorithms (e.g., autoencoders) to reduce the L1-scouting dataset size. Autoencoders are also a promising algorithm for anomaly detection, and so they will also be explored for that purpose, that can be already applicable to Run 3 data. For this task, we would also work on optimizing the hardware design of the algorithm (resource consumption and latency), to potentially run it as part of the main L1 trigger system to add scouting, both for Run3 and HL-LHC.
Publications and other resources
- Jennifer Ngadiuba, Presentation at ICHEP 2024, 18/07/2024, “Transforming the LHC Physics Program with AI”
- Noah Zipper, Presentation at FastML24, 15/10/2024, “Real-time Anomaly Detection in the CMS Experiment“
- Melissa Quinnan, Presentation at CHEP2024, 24/10/2024, “Anomaly Detection in the CMS L1 Trigger”
- Jennifer Ngadiuba, Presentation at ML4JETS, 04/11/2024, “Experimental highlights: Edge AI for particle physics”