Towards an Interpretable Data-driven Trigger System for High-throughput Physics Facilities

04/14/2021
by   Chinmaya Mahesh, et al.
16

Data-intensive science is increasingly reliant on real-time processing capabilities and machine learning workflows, in order to filter and analyze the extreme volumes of data being collected. This is especially true at the energy and intensity frontiers of particle physics where bandwidths of raw data can exceed 100 Tb/s of heterogeneous, high-dimensional data sourced from hundreds of millions of individual sensors. In this paper, we introduce a new data-driven approach for designing and optimizing high-throughput data filtering and trigger systems such as those in use at physics facilities like the Large Hadron Collider (LHC). Concretely, our goal is to design a data-driven filtering system with a minimal run-time cost for determining which data event to keep, while preserving (and potentially improving upon) the distribution of the output as generated by the hand-designed trigger system. We introduce key insights from interpretable predictive modeling and cost-sensitive learning in order to account for non-local inefficiencies in the current paradigm and construct a cost-effective data filtering and trigger model that does not compromise physics coverage.

READ FULL TEXT

page 2

page 5

research
03/15/2022

Innovations in trigger and data acquisition systems for next-generation physics facilities

Data-intensive physics facilities are increasingly reliant on heterogene...
research
02/12/2023

Machine Learning Assisted Bad Data Detection for High-throughput Substation Communication

Electrical substations are becoming more prone to cyber-attacks due to i...
research
07/24/2019

MadMiner: Machine learning-based inference for particle physics

The legacy measurements of the LHC will require analyzing high-dimension...
research
01/22/2021

Sparsistent filtering of comovement networks from high-dimensional data

Network filtering is an important form of dimension reduction to isolate...
research
10/05/2021

Inference and De-Noising of Non-Gaussian Particle Distribution Functions: A Generative Modeling Approach

The particle-in-cell numerical method of plasma physics balances a trade...
research
04/25/2018

JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics

In applications of machine learning to particle physics, a persistent ch...
research
11/01/2019

Mining Public Transit Ridership Flow and Origin-Destination Information from Wi-Fi and Bluetooth Sensing Data

Transit ridership flow and origin-destination (O-D) information is essen...

Please sign up or login with your details

Forgot password? Click here to reset