CPAD 2019 in Madison Wisconsin

Session

Machine Learning, Trigger and DAQ

Dec 8, 2019, 3:30 PM

Monona Terrace Convention Center

Conveners

Machine Learning, Trigger and DAQ

• Isobel Ojalvo (University Wisconsin Madison)
• Verena Ingrid Martinez Outschoorn (University of Massachusetts Amherst)

Machine Learning, Trigger and DAQ

• Verena Ingrid Martinez Outschoorn (University of Massachusetts Amherst)
• Isobel Ojalvo (University Wisconsin Madison)

139. Detector Data Acquisition Concepts

Ryan Herbst (SLAC)

12/8/19, 3:30 PM

6. hls4ml: deploying deep learning on FPGAs for L1 trigger and Data Acquisition

Sergo Jindariani (Fermilab)

12/8/19, 3:55 PM

Machine Learning, Trigger and DAQ

Talk

Machine learning is becoming ubiquitous across HEP. There is great potential to improve trigger and DAQ performance, and potentially in other real-time controls applications. However, the exploration of such techniques within the field in low latency/power FPGAs has just begun. We present hls4ml, a user-friendly software, based on High-Level Synthesis (HLS), designed to deploy network...

25. Machine Learning based algorithm for reconstructing prompt and displaced muons at Level-1 in CMS detector.

Jia Fu Low (University of Florida)

12/8/19, 4:20 PM

Machine Learning, Trigger and DAQ

Talk

"In order to preserve its ability to do physics at the electroweak scale in the HL-LHC era, the CMS experiment has to maintain low trigger thresholds that are robust against the large number of interactions per bunch crossing expected at the HL-LHC. Specifically, the Level-1 (L1) reconstruction algorithms for prompt muon triggers need significant improvement. Moreover, there is an emerging...

62. Detect New Physics with Deep Learning Trigger at the LHC

Dr Zhenbin Wu (University of Illinois at Chicago)

12/8/19, 4:45 PM

Machine Learning, Trigger and DAQ

Talk

The Large Hadron Collider has an enormous potential of discovering physics beyond the Standard Model, given the unprecedented collision energy and the large variety of production mechanisms that proton-proton collisions can probe. Unfortunately, only a small fraction of the produced events can be studied, while the majority of the events are rejected by the online filtering system. One is...

75. Machine Learning-based Trigger for DUNE

Guanqun Ge (Columbia University)

12/8/19, 5:10 PM

Machine Learning, Trigger and DAQ

Talk

The Deep Underground Neutrino Experiment (DUNE) is a planned, next-generation experiment that will use the liquid-argon time projection chamber (TPC) technology to study three-neutrino oscillations and search for rare physics processes. DUNE will have four far detector modules, each 10 ktons in fiducial mass. From just one of those modules, the TPC raw data will be streamed out of the DUNE...

138. Accelerated machine learning inference as a service for particle physics computing

Nhan Tran (Fermilab)

12/8/19, 5:35 PM

Talk

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as GPUs and Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in...

140. Challenges and R&D for DAQ in Particle Physics Experiment

Dr Kai Chen (Brookhaven National Laboratory)

12/9/19, 1:30 PM

26. Particle Flow at 40MHz with the CMS L1 Trigger

Mr T. Christian Herwig (FNAL)

12/9/19, 1:55 PM

Machine Learning, Trigger and DAQ

Talk

Following the High-Luminosity upgrade to the LHC, the CMS Level-1 (L1) Trigger will be overhauled to allow the efficient selection of diverse physics signatures at 40 MHz in an environment of up to 200 simultaneous proton-proton collisions. The L1 Trigger will combine information from the tracking, calorimeter, and muon systems to establish a list of single-particle candidates for each event...

32. Ideas for real-time analysis for HL-LHC using the CMS DAQ system

Remi Mommsen (Fermilab)

12/9/19, 2:20 PM

Machine Learning, Trigger and DAQ

Talk

The CMS experiment will be upgraded for operation at the High-Luminosity LHC to maintain and extend its optimal physics performance under extreme pileup conditions. Upgrades will include an entirely new tracking system, supplemented by a track trigger processor capable of providing tracks at Level-1, as well as a high-granularity calorimeter in the endcap region. New front-end and back-end...

74. The MicroBooNE Continuous Readout Stream for the Detection of Supernova Neutrinos

Iris Ponce (Research Assistant)

12/9/19, 2:45 PM

Machine Learning, Trigger and DAQ

Talk

MicroBooNE is a liquid argon time projection chamber (LArTPC) neutrino experiment located on the Booster Neutrino Beamline (BNB) at Fermilab. MicroBooNE has two operating readout streams; an externally-triggered stream used for MicroBooNE’s primary research goals to study BNB neutrinos and their interactions on argon, and, in parallel, a continuous stream of data dedicated for the detection of...

119. The trigger and real-time reconstruction at LHCb

Dr Daniel Craik (MIT)

12/9/19, 3:10 PM

Machine Learning, Trigger and DAQ

Talk

In this talk, I will present an overview of the LHCb trigger during Runs I and II, including real-time calibration of the detector, and detail plans for the trigger to be used during Run III of the experiment. For Run III data-taking, the level-0 hardware trigger used in the previous runs has been removed, requiring the first stage of the software trigger to process events at the LHC...

87. The SBND Trigger

David Rivera (University of Pennsylvania)

12/9/19, 3:35 PM

Machine Learning, Trigger and DAQ

Talk

The Short Baseline Neutrino (SBN) program at Fermilab will search for neutrino oscillations occurring over a 600m baseline with sensitivity to $\mathrm{\Delta }{m}^2$ of order 1eV${}^2$. As the name implies, the Short Baseline Near Detector (SBND), will serve as the near detector for the SBN program and will constrain the systematic uncertainties for the oscillation search by sampling the unoscillated...