15–18 Oct 2024
Purdue University
America/Indiana/Indianapolis timezone

Towards Online Machine Learning in DUNE Data Acquisition

15 Oct 2024, 15:45
5m
Steward Center 306 (Third floor) (Purdue University)

Steward Center 306 (Third floor)

Purdue University

128 Memorial Mall Dr, West Lafayette, IN 47907
Lightning 5 min talk + poster Lighting talks

Speaker

Andrew Mogan

Description

Processing large volumes of sparse neutrino interaction data is essential to the success of liquid argon time projection chamber (LArTPC) experiments such as DUNE. High rates of radiological background must be eliminated to extract critical information for track reconstruction and downstream analysis. Given the computational load of this rejection, and potential real time constraints of downstream analysis for certain physics applications, we propose the integration of machine learning based online data filtering into DUNE's data acquisition (DAQ) software through the Services for Optimized Network Inference on Coprocessors (SONIC) framework. This talk presents the current status of data processing methods for online data filtering within DUNE-DAQ. We show the status of implementing the NVIDIA Triton client-server model into DUNE DAQ, and compare directly to a real-time FGPA-based implementation from raw WIB readout data. We use the physics case of supernova pointing to benchmark the signal efficiency, latency, and throughput of our ML algorithms under various input and hardware configurations.

Author

Co-authors

Bonnie King (Fermi National Accelerator Lab. (US)) Georgia Karagiorgi Jennifer Ngadiuba (FNAL) Jovan Mitrevski (Fermi National Accelerator Lab. (US)) Kate Scholberg (Duke University) Maira Khan (Fermi National Accelerator Laboratory) Michael H L Wang Nhan Tran (Fermi National Accelerator Lab. (US)) Olivia Dalager (Fermilab)

Presentation materials